Localized instance fusion of MRI data of Alzheimer’s disease for classification based on instance transfer ensemble learning
Abstract Background Diagnosis of Alzheimer’s disease (AD) is very important, and MRI is an effective imaging mode of Alzheimer’s disease. There are many existing studies on the diagnosis of Alzheimer’s disease based on MRI data. However, there are no studies on the transfer learning between differen...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2018-05-01
|
Series: | BioMedical Engineering OnLine |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12938-018-0489-1 |
id |
doaj-d29a7dbc80954cbab705d44bc2253ca8 |
---|---|
record_format |
Article |
spelling |
doaj-d29a7dbc80954cbab705d44bc2253ca82020-11-24T21:07:50ZengBMCBioMedical Engineering OnLine1475-925X2018-05-0117111710.1186/s12938-018-0489-1Localized instance fusion of MRI data of Alzheimer’s disease for classification based on instance transfer ensemble learningXiaoheng Tan0Yuchuan Liu1Yongming Li2Pin Wang3Xiaoping Zeng4Fang Yan5Xinke Li6College of Communication Engineering, Chongqing UniversityCollege of Communication Engineering, Chongqing UniversityCollege of Communication Engineering, Chongqing UniversityCollege of Communication Engineering, Chongqing UniversityCollege of Communication Engineering, Chongqing UniversityCollege of Communication Engineering, Chongqing UniversityCollege of Communication Engineering, Chongqing UniversityAbstract Background Diagnosis of Alzheimer’s disease (AD) is very important, and MRI is an effective imaging mode of Alzheimer’s disease. There are many existing studies on the diagnosis of Alzheimer’s disease based on MRI data. However, there are no studies on the transfer learning between different datasets (including different subjects), thereby improving the sample size of target dataset indirectly. Methods Therefore, a new framework method is proposed in this paper to solve this problem. First, gravity transfer is used to transfer the source domain data closer to the target data set. Secondly, the best deviation between the transferred source domain samples and the target domain samples is searched by instance transfer learning algorithm (ITL) based on wrapper mode, thereby obtaining optimal transferred domain samples. Finally, the optimal transferred domain samples and the target domain training samples are combined for classification. If the source data and the target data have different features, a feature growing algorithm is proposed to solve this problem. Results The experimental results show that the proposed method is effective regardless of different kernel functions, different number of samples and different parameters. Besides, the transferred source domain samples by ITL algorithm can enlarge the target domain training samples and assist to improve the classification accuracy significantly. Conclusions Therefore, the study can enlarge the samples of AD by instance transfer learning, thereby being helpful for the small sample problems of AD. Since the proposed algorithm is a framework algorithm, the study is heuristics to the relevant researchers.http://link.springer.com/article/10.1186/s12938-018-0489-1Alzheimer’s diseaseMagnetic resonance imagingInstance transfer learningClassificationLocalized instance fusion |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xiaoheng Tan Yuchuan Liu Yongming Li Pin Wang Xiaoping Zeng Fang Yan Xinke Li |
spellingShingle |
Xiaoheng Tan Yuchuan Liu Yongming Li Pin Wang Xiaoping Zeng Fang Yan Xinke Li Localized instance fusion of MRI data of Alzheimer’s disease for classification based on instance transfer ensemble learning BioMedical Engineering OnLine Alzheimer’s disease Magnetic resonance imaging Instance transfer learning Classification Localized instance fusion |
author_facet |
Xiaoheng Tan Yuchuan Liu Yongming Li Pin Wang Xiaoping Zeng Fang Yan Xinke Li |
author_sort |
Xiaoheng Tan |
title |
Localized instance fusion of MRI data of Alzheimer’s disease for classification based on instance transfer ensemble learning |
title_short |
Localized instance fusion of MRI data of Alzheimer’s disease for classification based on instance transfer ensemble learning |
title_full |
Localized instance fusion of MRI data of Alzheimer’s disease for classification based on instance transfer ensemble learning |
title_fullStr |
Localized instance fusion of MRI data of Alzheimer’s disease for classification based on instance transfer ensemble learning |
title_full_unstemmed |
Localized instance fusion of MRI data of Alzheimer’s disease for classification based on instance transfer ensemble learning |
title_sort |
localized instance fusion of mri data of alzheimer’s disease for classification based on instance transfer ensemble learning |
publisher |
BMC |
series |
BioMedical Engineering OnLine |
issn |
1475-925X |
publishDate |
2018-05-01 |
description |
Abstract Background Diagnosis of Alzheimer’s disease (AD) is very important, and MRI is an effective imaging mode of Alzheimer’s disease. There are many existing studies on the diagnosis of Alzheimer’s disease based on MRI data. However, there are no studies on the transfer learning between different datasets (including different subjects), thereby improving the sample size of target dataset indirectly. Methods Therefore, a new framework method is proposed in this paper to solve this problem. First, gravity transfer is used to transfer the source domain data closer to the target data set. Secondly, the best deviation between the transferred source domain samples and the target domain samples is searched by instance transfer learning algorithm (ITL) based on wrapper mode, thereby obtaining optimal transferred domain samples. Finally, the optimal transferred domain samples and the target domain training samples are combined for classification. If the source data and the target data have different features, a feature growing algorithm is proposed to solve this problem. Results The experimental results show that the proposed method is effective regardless of different kernel functions, different number of samples and different parameters. Besides, the transferred source domain samples by ITL algorithm can enlarge the target domain training samples and assist to improve the classification accuracy significantly. Conclusions Therefore, the study can enlarge the samples of AD by instance transfer learning, thereby being helpful for the small sample problems of AD. Since the proposed algorithm is a framework algorithm, the study is heuristics to the relevant researchers. |
topic |
Alzheimer’s disease Magnetic resonance imaging Instance transfer learning Classification Localized instance fusion |
url |
http://link.springer.com/article/10.1186/s12938-018-0489-1 |
work_keys_str_mv |
AT xiaohengtan localizedinstancefusionofmridataofalzheimersdiseaseforclassificationbasedoninstancetransferensemblelearning AT yuchuanliu localizedinstancefusionofmridataofalzheimersdiseaseforclassificationbasedoninstancetransferensemblelearning AT yongmingli localizedinstancefusionofmridataofalzheimersdiseaseforclassificationbasedoninstancetransferensemblelearning AT pinwang localizedinstancefusionofmridataofalzheimersdiseaseforclassificationbasedoninstancetransferensemblelearning AT xiaopingzeng localizedinstancefusionofmridataofalzheimersdiseaseforclassificationbasedoninstancetransferensemblelearning AT fangyan localizedinstancefusionofmridataofalzheimersdiseaseforclassificationbasedoninstancetransferensemblelearning AT xinkeli localizedinstancefusionofmridataofalzheimersdiseaseforclassificationbasedoninstancetransferensemblelearning |
_version_ |
1716761954870099968 |