Dataset-Aware Preprocessing for Hippocampal Segmentation: Insights from Ablation and Transfer Learning
Bibliographic record
Abstract
Accurate hippocampal segmentation in 3D MRI is essential for neurodegenerative disease research and diagnosis. Preprocessing pipelines can strongly influence segmentation accuracy, yet their impact across datasets and in transfer learning scenarios remains underexplored. This study systematically compares a No Preprocessing (NP) pipeline and a Full Preprocessing (FP) pipeline for hippocampal segmentation on the EADC-ADNI HarP clinical dataset and the multi-site MSD dataset using a 3D U-Net with residual connections and dropout regularization. Evaluations employed standard overlap metrics, Hausdorff Distance (HD), and Wilcoxon signed-rank tests, complemented by qualitative analysis. Results show that NP consistently outperformed FP in Dice, Jaccard, and F1 metrics on HarP (e.g., Dice 0.8876 vs. 0.8753, p < 0.05), while FP achieved superior HD, indicating better boundary precision. Similar trends emerged in transfer learning from MSD to HarP, with NP improving overlap measures and FP maintaining lower HD. To test whether the findings generalize across architectures, experiments on Harp Dataset were also repeated with a 3D V-Net backbone, which reproduced the same trend. Comparative analysis with recent studies confirmed the competitiveness of the proposed approach despite lower input resolution and reduced model complexity. These findings highlight that preprocessing choice should be tailored to dataset characteristics and the target evaluation metric. The results provide practical guidance for selecting segmentation workflows in clinical and multi-center neuroimaging applications.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".