Multi-modal MRI analysis with disease-specific spatial filtering: initial testing to predict mild cognitive impairment patients who convert to Alzheimer’s disease
Background: Alterations of the gray and white matter have been identified in Alzheimer’s disease (AD) by structural MRI and diffusion tensor imaging (DTI). However, whether the combination of these modalities could increase the diagnostic performance is unknown.Methods: Participants included 19 AD p...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2011-08-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fneur.2011.00054/full |
| _version_ | 1818132951171334144 |
|---|---|
| author | Kenichi eOishi Kazi eAkhter Michelle eMielke Can eCeritoglu Jiangyang eZhang Hangyi eJiang Xin eLi Laurent eYounes Michael I Miller Peter evan Zijl Peter evan Zijl Marilyn eAlbert Constantine eLyketsos Susumu eMori Susumu eMori |
| author_facet | Kenichi eOishi Kazi eAkhter Michelle eMielke Can eCeritoglu Jiangyang eZhang Hangyi eJiang Xin eLi Laurent eYounes Michael I Miller Peter evan Zijl Peter evan Zijl Marilyn eAlbert Constantine eLyketsos Susumu eMori Susumu eMori |
| author_sort | Kenichi eOishi |
| collection | DOAJ |
| description | Background: Alterations of the gray and white matter have been identified in Alzheimer’s disease (AD) by structural MRI and diffusion tensor imaging (DTI). However, whether the combination of these modalities could increase the diagnostic performance is unknown.Methods: Participants included 19 AD patients, 22 amnestic mild cognitive impairment (aMCI) patients, and 22 cognitively normal elderly (NC). The aMCI group was further divided into an aMCI-converter group (converted to AD dementia within three years), and an aMCI-stable group who did not convert in this time period. A T1-weighted image, a T2 map, and a DTI of each participant were normalized, and voxel-based comparisons between AD and NC groups were performed. Regions-of-interest, which defined the areas with significant differences between AD and NC, were created for each modality and named disease-specific spatial filters (DSF). Linear discriminant analysis was used to optimize the combination of multiple MRI measurements extracted by DSF to effectively differentiate AD from NC. The resultant DSF and the discriminant function were applied to the aMCI group to investigate the power to differentiate the aMCI-converters from the aMCI-stable patients. Results: The multi-modal approach with AD-specific filters led to a predictive model with an area under the receiver operating characteristic curve (AUC) of 0.93, in differentiating aMCI-converters from aMCI-stable patients. This AUC was better than that of a single-contrast-based approach, such as T1-based morphometry or diffusion anisotropy analysis. Conclusion: The multi-modal approach has the potential to increase the value of MRI in predicting conversion from aMCI to AD. |
| first_indexed | 2024-12-11T08:44:59Z |
| format | Article |
| id | doaj.art-08fed9d26a804eb5a689e93510cb6b0c |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-12-11T08:44:59Z |
| publishDate | 2011-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-08fed9d26a804eb5a689e93510cb6b0c2022-12-22T01:14:10ZengFrontiers Media S.A.Frontiers in Neurology1664-22952011-08-01210.3389/fneur.2011.0005413750Multi-modal MRI analysis with disease-specific spatial filtering: initial testing to predict mild cognitive impairment patients who convert to Alzheimer’s diseaseKenichi eOishi0Kazi eAkhter1Michelle eMielke2Can eCeritoglu3Jiangyang eZhang4Hangyi eJiang5Xin eLi6Laurent eYounes7Michael I Miller8Peter evan Zijl9Peter evan Zijl10Marilyn eAlbert11Constantine eLyketsos12Susumu eMori13Susumu eMori14Johns Hopkins UniversityJohns Hopkins UniversityJohns Hopkins UniversityJohns Hopkins UniversityJohns Hopkins UniversityJohns Hopkins UniversityJohns Hopkins UniversityJohns Hopkins UniversityJohns Hopkins UniversityJohns Hopkins UniversityKennedy Krieger InstituteJohns Hopkins UniversityJohns Hopkins UniversityJohns Hopkins UniversityKennedy Krieger InstituteBackground: Alterations of the gray and white matter have been identified in Alzheimer’s disease (AD) by structural MRI and diffusion tensor imaging (DTI). However, whether the combination of these modalities could increase the diagnostic performance is unknown.Methods: Participants included 19 AD patients, 22 amnestic mild cognitive impairment (aMCI) patients, and 22 cognitively normal elderly (NC). The aMCI group was further divided into an aMCI-converter group (converted to AD dementia within three years), and an aMCI-stable group who did not convert in this time period. A T1-weighted image, a T2 map, and a DTI of each participant were normalized, and voxel-based comparisons between AD and NC groups were performed. Regions-of-interest, which defined the areas with significant differences between AD and NC, were created for each modality and named disease-specific spatial filters (DSF). Linear discriminant analysis was used to optimize the combination of multiple MRI measurements extracted by DSF to effectively differentiate AD from NC. The resultant DSF and the discriminant function were applied to the aMCI group to investigate the power to differentiate the aMCI-converters from the aMCI-stable patients. Results: The multi-modal approach with AD-specific filters led to a predictive model with an area under the receiver operating characteristic curve (AUC) of 0.93, in differentiating aMCI-converters from aMCI-stable patients. This AUC was better than that of a single-contrast-based approach, such as T1-based morphometry or diffusion anisotropy analysis. Conclusion: The multi-modal approach has the potential to increase the value of MRI in predicting conversion from aMCI to AD.http://journal.frontiersin.org/Journal/10.3389/fneur.2011.00054/fullDiffusion Tensor ImagingMagnetic Resonance ImagingMild Cognitive ImpairmentAlzheimer’s diseasewhite mattermulti-modal disease specific spatial filtering |
| spellingShingle | Kenichi eOishi Kazi eAkhter Michelle eMielke Can eCeritoglu Jiangyang eZhang Hangyi eJiang Xin eLi Laurent eYounes Michael I Miller Peter evan Zijl Peter evan Zijl Marilyn eAlbert Constantine eLyketsos Susumu eMori Susumu eMori Multi-modal MRI analysis with disease-specific spatial filtering: initial testing to predict mild cognitive impairment patients who convert to Alzheimer’s disease Frontiers in Neurology Diffusion Tensor Imaging Magnetic Resonance Imaging Mild Cognitive Impairment Alzheimer’s disease white matter multi-modal disease specific spatial filtering |
| title | Multi-modal MRI analysis with disease-specific spatial filtering: initial testing to predict mild cognitive impairment patients who convert to Alzheimer’s disease |
| title_full | Multi-modal MRI analysis with disease-specific spatial filtering: initial testing to predict mild cognitive impairment patients who convert to Alzheimer’s disease |
| title_fullStr | Multi-modal MRI analysis with disease-specific spatial filtering: initial testing to predict mild cognitive impairment patients who convert to Alzheimer’s disease |
| title_full_unstemmed | Multi-modal MRI analysis with disease-specific spatial filtering: initial testing to predict mild cognitive impairment patients who convert to Alzheimer’s disease |
| title_short | Multi-modal MRI analysis with disease-specific spatial filtering: initial testing to predict mild cognitive impairment patients who convert to Alzheimer’s disease |
| title_sort | multi modal mri analysis with disease specific spatial filtering initial testing to predict mild cognitive impairment patients who convert to alzheimer s disease |
| topic | Diffusion Tensor Imaging Magnetic Resonance Imaging Mild Cognitive Impairment Alzheimer’s disease white matter multi-modal disease specific spatial filtering |
| url | http://journal.frontiersin.org/Journal/10.3389/fneur.2011.00054/full |
| work_keys_str_mv | AT kenichieoishi multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT kazieakhter multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT michelleemielke multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT caneceritoglu multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT jiangyangezhang multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT hangyiejiang multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT xineli multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT laurenteyounes multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT michaelimiller multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT peterevanzijl multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT peterevanzijl multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT marilynealbert multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT constantineelyketsos multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT susumuemori multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease AT susumuemori multimodalmrianalysiswithdiseasespecificspatialfilteringinitialtestingtopredictmildcognitiveimpairmentpatientswhoconverttoalzheimersdisease |