Analysis of 2D and 3D Convolution Models for Volumetric Segmentation of the Human Hippocampus
Bibliographic record
Abstract
Extensive medical research has revealed evidence of a strong association between hippocampus atrophy and age-related diseases such as Alzheimer’s disease (AD). Therefore; segmentation of the hippocampus is an important task that can help clinicians and researchers in diagnosing cognitive impairment and uncovering the mechanisms behind hippocampal changes and diseases of the brain. The main aim of this paper was to provide a fair comparison of 2D and 3D convolution-based architectures for the specific task of hippocampus segmentation from brain MRI volumes to determine whether 3D convolution models truly perform better in hippocampus segmentation and also to assess any additional costs in terms of time and computational resources. Our optimized model, which used 50 epochs and a mini-batch size of 2, achieved the best validation loss and Dice Similarity Score (DSC) of 0.0129 and 0.8541, respectively, across all experiment runs. Based on the model comparisons, we concluded that 2D convolution models can surpass their 3D counterparts in terms of both hippocampus segmentation performance and training efficiency. Our automatic hippocampus segmentation demonstrated potential savings of thousands of clinician person-hours spent on manually analyzing and segmenting brain MRI scans
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".