P2‐242: An automated and robust algorithm to measure changes in medial temporal lobe volume in early Alzheimer's disease
Bibliographic record
Abstract
The medial temporal lobe (MTL) including the hippocampus is known to atrophy as Alzheimer disease (AD) progresses. Manual segmentation of the MTL on magnetic resonance images (MRI) is time-consuming and subjective but considered the gold standard due to difficulty in automatic identification of some tissue boundaries. The purpose of this work was to develop a fully automated method to quantify the change in MTL volume over time that maximizes measurement precision at the expense of anatomical accuracy. The Expectation Maximization (EM) segmentation is a model-based classification method used to define gray matter, white matter, and cerebrospinal fluid in baseline images. An atlas-based registration method was then used to define the MTL region of interest (ROI) on the gray matter pixels. A seeded region-growing algorithm was applied to the MTL ROI to smooth strongly-visible boundaries. Baseline images were registered to 24 months follow-up images using a deformable registration algorithm to propagate the MTL ROI defined on the baseline images and measure the change in volume. T1-weighted MP-RAGE MRI images acquired at baseline and at 24 months in 24 normal elderly subjects, 25 subjects with mild cognitive impairment (MCI) and 25 subjects with AD were randomly selected from the A lzheimer Disease Neuroimaging Initiative (ADNI) database to test the algorithm. The accuracy and precision were determined using 100 volumetric image sets of a cube phantom with known volume. The known volume (mean ± STD) of the cube phantom was underestimated by 3% ± 0.04%. The repeated measures t- test showed that there was a significant decrease (p <0.0001) in MTL volume in AD subjects. The MTL volume changes between baseline and 24 months (Mean±SEM, 75 ± 46 mm 3 in the normal elderly, 45 ± 38 mm 3 in subjects with MCI, and 242 ± 43 mm 3 in subjects with AD) were significantly different between groups (P <0.01). The Tukey post-hoc analysis showed a significant difference between AD and normal elderly (P <0.05); AD and MCI subjects (P <0.01). A fully automated segmentation method to measure MTL volume changes detected increased atrophy in the MTL in subjects with AD compared to MCI and control subjects.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".