SU91. Evaluating Accuracy of Basal Ganglia Segmentation Methods: Comparing Automated Approaches to Manual Delineation
Bibliographic record
Abstract
Background: Accurate automated quantification of subcortical structures is a greatly pursued endeavor in neuroimaging. To establish the validity and reliability of these methods in defining the basal ganglia and thalamus, we investigated differences in volumetry between manual delineation and automated segmentations derived by FreeSurfer, FSL, and MAGeT in a sample of first-episode psychosis (FEP) patients and controls. Methods: The basal ganglia and thalamus of 30 subjects (15 FEP, 15 controls) were manually defined and compared to automated methods by extracting: (1) percent volume differences between manual volumes and those derived by MAGeT/FreeSurfer/FSL, (2) between-method correlations, and (3) Bland-Altman plots to illustrate potential biases. Volume and shape differences of the basal ganglia and thalamus were also examined in a larger sample of 135 FEP patients and 88 controls across automated techniques. Results: All automated methods overestimated volumes compared to manual segmentations, with the least pronounced differences produced with MAGeT. The least between-method variability was noted for the striatum, whereas marked differences between manual labels and MAGeT compared to FreeSurfer and FSL emerged for the pallidum and thalamus. Correlations between manual segmentation and automated methods were strongest for MAGeT (range: 0.51–0.92; P < .01, corrected), whereas FreeSurfer and FSL showed moderate to strong Pearson correlations (range: 0.44–0.86; P < .05, corrected), with the exception of FreeSurfer pallidal (r = 0.31, P = .10) and FSL thalamic segmentations (r = 0.37, P = .051). Bland-Altman plots highlighted a tendency for greater volumetric differences between manual labels and automated methods at the lower end of the distribution (ie, smaller structures), which was most prominent for bilateral thalamus across automated pipelines, and left pallidum for FSL. The striatum and pallidum were significantly larger in FEP patients compared to controls bilaterally, irrespective of method. MAGeT was more sensitive to shape-based group differences, and uncovered widespread surface expansions in the striatum and pallidum bilaterally in FEP patients compared to controls, and contractions in bilateral thalamus (FDR corrected). By contrast, FSL only detected differences in the right ventral striatum (FEP > control, corrected) and one cluster of the left thalamus (Control > FEP, corrected). Conclusion: The current study provides a detailed analysis of how manual segmentations of the basal ganglia and thalamus compare against 3 automated segmentation pipelines, namely MAGeT, FreeSurfer, and FSL, in the clinical investigation of changes in subcortical structures in FEP. Results obtained with automated pipelines should be rigorously checked by a trained eye, and consistent quality control procedures are strongly encouraged when using automated segmentation methods.
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 | 0.025 | 0.063 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".