Prediction of conversion from mild cognitive impairment to Alzheimer’s disease using MRI and structural network features
Optimized magnetic resonance imaging (MRI) features and abnormalities of brain network architectures may allow earlier detection and accurate prediction of the progression from mild cognitive impairment (MCI) to Alzheimer’s disease (AD). In this study, we proposed a classification framework to disti...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2016-04-01
|
| Series: | Frontiers in Aging Neuroscience |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fnagi.2016.00076/full |
| _version_ | 1818475737435340800 |
|---|---|
| author | Rizhen eWei Chuhan eLi Noa eFogelson Ling eLi |
| author_facet | Rizhen eWei Chuhan eLi Noa eFogelson Ling eLi |
| author_sort | Rizhen eWei |
| collection | DOAJ |
| description | Optimized magnetic resonance imaging (MRI) features and abnormalities of brain network architectures may allow earlier detection and accurate prediction of the progression from mild cognitive impairment (MCI) to Alzheimer’s disease (AD). In this study, we proposed a classification framework to distinguish MCI converters (MCIc) from MCI non-converters (MCInc) by using a combination of FreeSurfer-derived MRI features and nodal features derived from the thickness network. At the feature selection step, we first employed sparse linear regression with stability selection, for the selection of discriminative features in the iterative combinations of MRI and network measures. Subsequently the top K features of available combinations were selected as optimal features for classification. To obtain unbiased results, support vector machine (SVM) classifiers with nested cross validation were used for classification. The combination of 10 features including those from MRI and network measures attained accuracies of 66.04%, 76.39%, 74.66% and 73.91% for mixed conversion time, 6, 12 and 18 months before diagnosis of probable AD, respectively. Analysis of the diagnostic power of different time periods before diagnosis of probable AD showed that short-term prediction (6 and 12 months) achieved more stable and higher AUC scores compared with long-term prediction (18 months), with K values from 1 to 30. The present results suggest that meaningful predictors composed of MRI and network measures may offer the possibility for early detection of progression from MCI to AD. |
| first_indexed | 2024-12-10T09:16:32Z |
| format | Article |
| id | doaj.art-95d005770f284ace8bbf09aca8d25dfb |
| institution | Directory Open Access Journal |
| issn | 1663-4365 |
| language | English |
| last_indexed | 2024-12-10T09:16:32Z |
| publishDate | 2016-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Aging Neuroscience |
| spelling | doaj.art-95d005770f284ace8bbf09aca8d25dfb2022-12-22T01:54:51ZengFrontiers Media S.A.Frontiers in Aging Neuroscience1663-43652016-04-01810.3389/fnagi.2016.00076185209Prediction of conversion from mild cognitive impairment to Alzheimer’s disease using MRI and structural network featuresRizhen eWei0Chuhan eLi1Noa eFogelson2Ling eLi3University of Electronic Science and Technology of ChinaUniversity of Electronic Science and Technology of ChinaEEG and Cognition Laboratory, University of A CoruñaUniversity of Electronic Science and Technology of ChinaOptimized magnetic resonance imaging (MRI) features and abnormalities of brain network architectures may allow earlier detection and accurate prediction of the progression from mild cognitive impairment (MCI) to Alzheimer’s disease (AD). In this study, we proposed a classification framework to distinguish MCI converters (MCIc) from MCI non-converters (MCInc) by using a combination of FreeSurfer-derived MRI features and nodal features derived from the thickness network. At the feature selection step, we first employed sparse linear regression with stability selection, for the selection of discriminative features in the iterative combinations of MRI and network measures. Subsequently the top K features of available combinations were selected as optimal features for classification. To obtain unbiased results, support vector machine (SVM) classifiers with nested cross validation were used for classification. The combination of 10 features including those from MRI and network measures attained accuracies of 66.04%, 76.39%, 74.66% and 73.91% for mixed conversion time, 6, 12 and 18 months before diagnosis of probable AD, respectively. Analysis of the diagnostic power of different time periods before diagnosis of probable AD showed that short-term prediction (6 and 12 months) achieved more stable and higher AUC scores compared with long-term prediction (18 months), with K values from 1 to 30. The present results suggest that meaningful predictors composed of MRI and network measures may offer the possibility for early detection of progression from MCI to AD.http://journal.frontiersin.org/Journal/10.3389/fnagi.2016.00076/fullMild Cognitive ImpairmentMRIpredictionEarly detectionStructural network |
| spellingShingle | Rizhen eWei Chuhan eLi Noa eFogelson Ling eLi Prediction of conversion from mild cognitive impairment to Alzheimer’s disease using MRI and structural network features Frontiers in Aging Neuroscience Mild Cognitive Impairment MRI prediction Early detection Structural network |
| title | Prediction of conversion from mild cognitive impairment to Alzheimer’s disease using MRI and structural network features |
| title_full | Prediction of conversion from mild cognitive impairment to Alzheimer’s disease using MRI and structural network features |
| title_fullStr | Prediction of conversion from mild cognitive impairment to Alzheimer’s disease using MRI and structural network features |
| title_full_unstemmed | Prediction of conversion from mild cognitive impairment to Alzheimer’s disease using MRI and structural network features |
| title_short | Prediction of conversion from mild cognitive impairment to Alzheimer’s disease using MRI and structural network features |
| title_sort | prediction of conversion from mild cognitive impairment to alzheimer s disease using mri and structural network features |
| topic | Mild Cognitive Impairment MRI prediction Early detection Structural network |
| url | http://journal.frontiersin.org/Journal/10.3389/fnagi.2016.00076/full |
| work_keys_str_mv | AT rizhenewei predictionofconversionfrommildcognitiveimpairmenttoalzheimersdiseaseusingmriandstructuralnetworkfeatures AT chuhaneli predictionofconversionfrommildcognitiveimpairmenttoalzheimersdiseaseusingmriandstructuralnetworkfeatures AT noaefogelson predictionofconversionfrommildcognitiveimpairmenttoalzheimersdiseaseusingmriandstructuralnetworkfeatures AT lingeli predictionofconversionfrommildcognitiveimpairmenttoalzheimersdiseaseusingmriandstructuralnetworkfeatures |