Assessing accuracy of automated segmentation methods for brain lateral ventricles in MRI data
Bibliographic record
Abstract
The incidence of Alzheimer’s disease (AD) has steadily increased over the last few decades. AD leads to a decreased quality of life for those affected, hence, there is an urgent need to identify a reference point that can assist in early identification of the presence of AD. An objective and sensitive measure that may assist in the detection of AD is the lateral ventricle volume. In high-resolution magnetic resonance (MR) images, a relationship between lateral ventricle enlargement and AD progression can be examined. Volumetric data analyses for the ventricles require that they be segmented by neuro-anatomy experts using manual tracing. Since manual segmentation methods are impractical due to time requirements and rater variability, automated methods are frequently used to reliably and accurately segment brain regions. Thus, our goal was to compare the performance of two automated segmentation methods, FreeSurfer (FS) and FreeSurfer combined with Large Deformation Diffeomorphic Metric Mapping label propagation (FS+LDDMM), for the task of lateral ventricle segmentation. The Dice Similarity Coefficient (DSC) was used to evaluate the segmentation accuracy obtained by these two automated methods. When compared to the manual segmentation labels, the FS+LDDMM method had a greater mean DSC than the FreeSurfer method. Moreover, the manual vs. FS+LDDMM DSC values ranged from 99-100, while manual vs. FreeSurfer ranged from 73-92. Both of these results illustrate that FS+LDDMM is an automated method that has a high degree of accuracy and can be used in place of manual segmentation, while FreeSurfer should only be used as a preliminary automatic 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 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 | 0.018 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.002 | 0.001 |
| 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".