PELICAN: a Longitudinal Image Processing Pipeline for Analyzing Structural Magnetic Resonance Images in Aging and Neurodegenerative Disease Populations
Bibliographic record
Abstract
Abstract Structural magnetic resonance imaging (MRI) allows for accurate non-invasive assessment of the brain’s structure and its longitudinal changes. Availability of large scale longitudinal MRI datasets enables us to probe brain changes in health and disease, and derive longitudinal trajectories of brain morphometry based measures to estimate brain atrophy and other disease-related abnormalities. In contrast to their cross-sectional counterparts, image processing pipelines that have been designed for longitudinal data can reduce noise in the derived measurements by disentangling the within and between subject variabilities, improving the sensitivity of the downstream models in detecting more subtle longitudinal changes. Here we present PELICAN, our open source multi-contrast longitudinal image processing pipeline, that has been designed and extensively validated for use in longitudinal settings and populations with neurodegenerative disorders. PELICAN can use population specific average templates as intermediate targets to derive accurate nonlinear registrations for cases with substantial levels of atrophy, which commonly used pipelines struggle to process. We evaluated PELICAN’s performance across over 34,000 MRIs from multiple aging and neurodegenerative disorder cohorts, and compared its reliability and failure rates against FreeSurfer as a widely used image processing tool, showing superior performance of PELICAN compared to FreeSurfer, both in terms of failure rate and reliability. Our results demonstrate that PELICAN can be used to accurately process MRIs of individuals with neurodegenerative disease who present with greater levels of atrophy and white matter lesion burden.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.012 | 0.005 |
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".