Longitudinal Analysis of Amyloid PET and Brain MRI for Predicting Conversion from Mild Cognitive Impairment to Alzheimer’s Disease: Findings from the ADNI Cohort
Background/Objectives: This study aimed to investigate the predictive power of integrated longitudinal amyloid positron emission tomography (PET) and brain magnetic resonance imaging (MRI) data for determining the likelihood of conversion to Alzheimer’s disease (AD) in patients with mild cognitive i...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Tomography |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2379-139X/11/3/37 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850087797042446336 |
|---|---|
| author | Do-Hoon Kim |
| author_facet | Do-Hoon Kim |
| author_sort | Do-Hoon Kim |
| collection | DOAJ |
| description | Background/Objectives: This study aimed to investigate the predictive power of integrated longitudinal amyloid positron emission tomography (PET) and brain magnetic resonance imaging (MRI) data for determining the likelihood of conversion to Alzheimer’s disease (AD) in patients with mild cognitive impairment (MCI). Methods: We included 180 patients with MCI from the Alzheimer’s Disease Neuroimaging Initiative, with baseline and 2-year follow-up scans obtained using F-18 florbetapir PET and MRI. Patients were categorized as converters (progressing to AD) or nonconverters based on a 6-year follow-up. Quantitative analyses included the calculation of amyloid burden using the standardized uptake value ratio (SUVR), brain amyloid smoothing scores (BASSs), brain atrophy indices (BAIs), and their integration into shape features. Longitudinal changes and receiver operating characteristic analyses assessed the predictive power of these biomarkers. Results: Among 180 patients with MCI, 76 (42.2%) were converters, who exhibited significantly higher baseline and 2-year follow-up values for SUVR, BASS, BAI, and shape features than nonconverters (<i>p</i> < 0.001). Shape features demonstrated the highest predictive accuracy for conversion, with areas under the curve of 0.891 at baseline and 0.898 at 2 years. Percent change analyses revealed significant increases in brain atrophy; amyloid deposition changes showed a paradoxical decrease in converters. Additionally, strong associations were observed between longitudinal changes in shape features and neuropsychological test results. Conclusions: The integration of amyloid PET and MRI biomarkers enhances the prediction of AD progression in patients with MCI. These findings support the potential of combined imaging approaches for early diagnosis and targeted interventions in AD. |
| format | Article |
| id | doaj-art-09fd226a586a4cc2aee050cefcafa458 |
| institution | DOAJ |
| issn | 2379-1381 2379-139X |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Tomography |
| spelling | doaj-art-09fd226a586a4cc2aee050cefcafa4582025-08-20T02:43:09ZengMDPI AGTomography2379-13812379-139X2025-03-011133710.3390/tomography11030037Longitudinal Analysis of Amyloid PET and Brain MRI for Predicting Conversion from Mild Cognitive Impairment to Alzheimer’s Disease: Findings from the ADNI CohortDo-Hoon Kim0Department of Nuclear Medicine, Daejeon Eulji Medical Center, Eulji University School of Medicine, Daejeon 35233, Republic of KoreaBackground/Objectives: This study aimed to investigate the predictive power of integrated longitudinal amyloid positron emission tomography (PET) and brain magnetic resonance imaging (MRI) data for determining the likelihood of conversion to Alzheimer’s disease (AD) in patients with mild cognitive impairment (MCI). Methods: We included 180 patients with MCI from the Alzheimer’s Disease Neuroimaging Initiative, with baseline and 2-year follow-up scans obtained using F-18 florbetapir PET and MRI. Patients were categorized as converters (progressing to AD) or nonconverters based on a 6-year follow-up. Quantitative analyses included the calculation of amyloid burden using the standardized uptake value ratio (SUVR), brain amyloid smoothing scores (BASSs), brain atrophy indices (BAIs), and their integration into shape features. Longitudinal changes and receiver operating characteristic analyses assessed the predictive power of these biomarkers. Results: Among 180 patients with MCI, 76 (42.2%) were converters, who exhibited significantly higher baseline and 2-year follow-up values for SUVR, BASS, BAI, and shape features than nonconverters (<i>p</i> < 0.001). Shape features demonstrated the highest predictive accuracy for conversion, with areas under the curve of 0.891 at baseline and 0.898 at 2 years. Percent change analyses revealed significant increases in brain atrophy; amyloid deposition changes showed a paradoxical decrease in converters. Additionally, strong associations were observed between longitudinal changes in shape features and neuropsychological test results. Conclusions: The integration of amyloid PET and MRI biomarkers enhances the prediction of AD progression in patients with MCI. These findings support the potential of combined imaging approaches for early diagnosis and targeted interventions in AD.https://www.mdpi.com/2379-139X/11/3/37imaging biomarkersAlzheimer’s diseaseshape featureAlzheimer’s disease neuroimaging initiative cohort |
| spellingShingle | Do-Hoon Kim Longitudinal Analysis of Amyloid PET and Brain MRI for Predicting Conversion from Mild Cognitive Impairment to Alzheimer’s Disease: Findings from the ADNI Cohort Tomography imaging biomarkers Alzheimer’s disease shape feature Alzheimer’s disease neuroimaging initiative cohort |
| title | Longitudinal Analysis of Amyloid PET and Brain MRI for Predicting Conversion from Mild Cognitive Impairment to Alzheimer’s Disease: Findings from the ADNI Cohort |
| title_full | Longitudinal Analysis of Amyloid PET and Brain MRI for Predicting Conversion from Mild Cognitive Impairment to Alzheimer’s Disease: Findings from the ADNI Cohort |
| title_fullStr | Longitudinal Analysis of Amyloid PET and Brain MRI for Predicting Conversion from Mild Cognitive Impairment to Alzheimer’s Disease: Findings from the ADNI Cohort |
| title_full_unstemmed | Longitudinal Analysis of Amyloid PET and Brain MRI for Predicting Conversion from Mild Cognitive Impairment to Alzheimer’s Disease: Findings from the ADNI Cohort |
| title_short | Longitudinal Analysis of Amyloid PET and Brain MRI for Predicting Conversion from Mild Cognitive Impairment to Alzheimer’s Disease: Findings from the ADNI Cohort |
| title_sort | longitudinal analysis of amyloid pet and brain mri for predicting conversion from mild cognitive impairment to alzheimer s disease findings from the adni cohort |
| topic | imaging biomarkers Alzheimer’s disease shape feature Alzheimer’s disease neuroimaging initiative cohort |
| url | https://www.mdpi.com/2379-139X/11/3/37 |
| work_keys_str_mv | AT dohoonkim longitudinalanalysisofamyloidpetandbrainmriforpredictingconversionfrommildcognitiveimpairmenttoalzheimersdiseasefindingsfromtheadnicohort |