Identify the Atrophy of Alzheimer’s Disease, Mild Cognitive Impairment and Normal Aging Using Morphometric MRI Analysis
Bibliographic record
Abstract
Quantitatively assessing the medial temporal lobe structures atrophy is vital for early diagnosis of Alzheimer's disease (AD) and accurately tracking of the disease progression. Morphometry characteristics such as gray matter volume (GMV) and cortical thickness have been proved to be valuable measurements of brain atrophy. In this study, we proposed a morphometric MRI analysis based method to explore the cross-sectional differences and longitudinal changes of GMV and cortical thickness in patients with AD, (mild cognitive impairment) MCI and the normal elderly. High resolution 3D MRI data was obtained from ADNI database. SPM8 plus DARTEL was carried out for data preprocessing. Two kinds of z-score map were calculated to respectively reflect the GMV and cortical thickness decline compared with age-matched normal control database (NCDB). A volume of interest (VOI) covering medial temporal lobe structures was defined by group comparison. Within this VOI, GMV and cortical thickness decline indicators were respectively defined as the mean of the negative z-scores and the sum of the normalized negative z-scores of the corresponding z-score map. Kruskal–Wallis test was applied to statistically identify group wise differences of the indicators. Support vector machines (SVM) based prediction was performed with a leave-one-out cross-validation design to evaluate the predictive accuracies of the indicators. Linear least squares estimation was utilized to assess the changing rate of the indicators for the three groups. Cross-sectional comparison of the baseline decline indicators revealed that the GMV and cortical thickness decline were more serious from NC, MCI to AD, with statistic significance. Using a multi-region based SVM model with the two indicators, the discrimination accuracy between AD and NC, MCI and NC, AD and MCI was 92.7%, 91.7%, 78.4% respectively. For three-way prediction, the accuracy was 74.6%. Furthermore, the proposed two indicators could also identify the atrophy rate differences among the three groups in longitudinal analysis. The proposed method could serve as an automatic and time-sparing approach for early diagnosis and tracking the progression of AD.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".