Automated registration-based skull stripping procedure for feline neuroimaging
Bibliographic record
Abstract
Skull stripping is a fundamental preprocessing step in modern neuroimaging analyses that consists of removing non-brain voxels from structural images. When performed entirely manually, this laborious step can be rate-limiting for analyses, with the potential to influence the population size chosen. This emphasizes the need for a fully- or semi-automated masking procedure to decrease man-hours without an associated decline in accuracy. These algorithms are plentiful in human neuroimaging but are relatively lacking for the plethora of animal species used in research. Unfortunately, software designed for humans cannot be easily transformed for animal use due to the high amount of tailoring required to accurately account for the considerable degree of variation within the highly folded human cortex. As most animals have a relatively less complex cerebral morphology, intersubject variability is consequently decreased, presenting the possibility to simply warp the brain mask of a template image into subject space for the purpose of skull stripping. This study presents the use of the Cat Automated Registration-based Skull Stripper (CARSS) tool on feline structural images. Validation metrics revealed that this method was able to perform on par with manual raters on >90 % of scans tested, and that its consistency across multiple runs was superior to that of masking performed by two independent raters. Additionally, CARSS outperformed three well-known skull stripping programs on the validation dataset. Despite a handful of manual interventions required, the presented tool reduced the man-hours required to skull strip 60 feline images over tenfold when compared to a fully manual approach, proving to be invaluable for feline neuroimaging studies, particularly those with large population sizes.
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.013 | 0.004 |
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".