On brain atlas choice and automatic segmentation methods: a comparison of MAPER & FreeSurfer using three atlas databases
Bibliographic record
Abstract
Several automatic image segmentation methods and few atlas databases exist for analysing structural T1-weighted magnetic resonance brain images. The impact of choosing a combination has not hitherto been described but may bias comparisons across studies. We evaluated two segmentation methods (MAPER and FreeSurfer), using three publicly available atlas databases (Hammers_mith, Desikan-Killiany-Tourville, and MICCAI 2012 Grand Challenge). For each combination of atlas and method, we conducted a leave-one-out cross-comparison to estimate the segmentation accuracy of FreeSurfer and MAPER. We also used each possible combination to segment two datasets of patients with known structural abnormalities (Alzheimer's disease (AD) and mesial temporal lobe epilepsy with hippocampal sclerosis (HS)) and their matched healthy controls. MAPER was better than FreeSurfer at modelling manual segmentations in the healthy control leave-one-out analyses in two of the three atlas databases, and the Hammers_mith atlas database transferred to new datasets best regardless of segmentation method. Both segmentation methods reliably identified known abnormalities in each patient group. Better separation was seen for FreeSurfer in the AD and left-HS datasets, and for MAPER in the right-HS dataset. We provide detailed quantitative comparisons for multiple anatomical regions, thus enabling researchers to make evidence-based decisions on their choice of atlas and segmentation method.
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 | 0.076 | 0.150 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.003 | 0.004 |
| Bibliometrics | 0.011 | 0.007 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.008 | 0.006 |
| Open science | 0.005 | 0.007 |
| Research integrity | 0.004 | 0.003 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".