A novel conversion prediction method of MCI to AD based on longitudinal dynamic morphological features using ADNI structural MRIs
Abstract Mild cognitive impairment (MCI) is a pre-existing state of Alzheimer's disease (AD). An accurate prediction on the conversion from MCI to AD is of vital clinical significance for potential prevention and treatment of AD. Longitudinal studies received widespread attention...
Main Authors: | , , , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
Springer Berlin Heidelberg
2021
|
Online Access: | https://hdl.handle.net/1721.1/131422 |
_version_ | 1811071616175570944 |
---|---|
author | Guo, Man Li, Yongchao Zheng, Weihao Huang, Keman Zhou, Li Hu, Xiping Yao, Zhijun Hu, Bin |
author2 | Sloan School of Management |
author_facet | Sloan School of Management Guo, Man Li, Yongchao Zheng, Weihao Huang, Keman Zhou, Li Hu, Xiping Yao, Zhijun Hu, Bin |
author_sort | Guo, Man |
collection | MIT |
description | Abstract
Mild cognitive impairment (MCI) is a pre-existing state of Alzheimer's disease (AD). An accurate prediction on the conversion from MCI to AD is of vital clinical significance for potential prevention and treatment of AD. Longitudinal studies received widespread attention for investigating the disease progression, though most studies did not sufficiently utilize the evolution information. In this paper, we proposed a cerebral similarity network with more progression information to predict the conversion from MCI to AD efficiently. First, we defined the new dynamic morphological feature to mine longitudinal information sufficiently. Second, based on the multiple dynamic morphological features the cerebral similarity network was constructed by sparse regression algorithm with optimized parameters to obtain better prediction performance. Then, leave-one-out cross-validation and support vector machine (SVM) were employed for the training and evaluation of the classifiers. The proposed methodology obtained a high accuracy of 92.31% (Sensitivity = 100%, Specificity = 82.86%) in a three-year ahead prediction of MCI to AD conversion. Experiment results suggest the effectiveness of the dynamic morphological feature, serving as a more sensitive biomarker in the prediction of MCI conversion. |
first_indexed | 2024-09-23T08:54:00Z |
format | Article |
id | mit-1721.1/131422 |
institution | Massachusetts Institute of Technology |
language | English |
last_indexed | 2024-09-23T08:54:00Z |
publishDate | 2021 |
publisher | Springer Berlin Heidelberg |
record_format | dspace |
spelling | mit-1721.1/1314222023-09-01T19:07:43Z A novel conversion prediction method of MCI to AD based on longitudinal dynamic morphological features using ADNI structural MRIs Guo, Man Li, Yongchao Zheng, Weihao Huang, Keman Zhou, Li Hu, Xiping Yao, Zhijun Hu, Bin Sloan School of Management Abstract Mild cognitive impairment (MCI) is a pre-existing state of Alzheimer's disease (AD). An accurate prediction on the conversion from MCI to AD is of vital clinical significance for potential prevention and treatment of AD. Longitudinal studies received widespread attention for investigating the disease progression, though most studies did not sufficiently utilize the evolution information. In this paper, we proposed a cerebral similarity network with more progression information to predict the conversion from MCI to AD efficiently. First, we defined the new dynamic morphological feature to mine longitudinal information sufficiently. Second, based on the multiple dynamic morphological features the cerebral similarity network was constructed by sparse regression algorithm with optimized parameters to obtain better prediction performance. Then, leave-one-out cross-validation and support vector machine (SVM) were employed for the training and evaluation of the classifiers. The proposed methodology obtained a high accuracy of 92.31% (Sensitivity = 100%, Specificity = 82.86%) in a three-year ahead prediction of MCI to AD conversion. Experiment results suggest the effectiveness of the dynamic morphological feature, serving as a more sensitive biomarker in the prediction of MCI conversion. 2021-09-20T17:17:00Z 2021-09-20T17:17:00Z 2020-06-04 2020-09-24T20:57:16Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/131422 en https://doi.org/10.1007/s00415-020-09890-5 Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. Springer-Verlag GmbH Germany, part of Springer Nature application/pdf Springer Berlin Heidelberg Springer Berlin Heidelberg |
spellingShingle | Guo, Man Li, Yongchao Zheng, Weihao Huang, Keman Zhou, Li Hu, Xiping Yao, Zhijun Hu, Bin A novel conversion prediction method of MCI to AD based on longitudinal dynamic morphological features using ADNI structural MRIs |
title | A novel conversion prediction method of MCI to AD based on longitudinal dynamic morphological features using ADNI structural MRIs |
title_full | A novel conversion prediction method of MCI to AD based on longitudinal dynamic morphological features using ADNI structural MRIs |
title_fullStr | A novel conversion prediction method of MCI to AD based on longitudinal dynamic morphological features using ADNI structural MRIs |
title_full_unstemmed | A novel conversion prediction method of MCI to AD based on longitudinal dynamic morphological features using ADNI structural MRIs |
title_short | A novel conversion prediction method of MCI to AD based on longitudinal dynamic morphological features using ADNI structural MRIs |
title_sort | novel conversion prediction method of mci to ad based on longitudinal dynamic morphological features using adni structural mris |
url | https://hdl.handle.net/1721.1/131422 |
work_keys_str_mv | AT guoman anovelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT liyongchao anovelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT zhengweihao anovelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT huangkeman anovelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT zhouli anovelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT huxiping anovelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT yaozhijun anovelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT hubin anovelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT guoman novelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT liyongchao novelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT zhengweihao novelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT huangkeman novelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT zhouli novelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT huxiping novelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT yaozhijun novelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris AT hubin novelconversionpredictionmethodofmcitoadbasedonlongitudinaldynamicmorphologicalfeaturesusingadnistructuralmris |