Differences in 129Xe MRI VDP using K-means, linear-binning and threshold approaches
Bibliographic record
Abstract
Rationale: Hyperpolarized 129Xe MRI quantifies ventilation heterogeneity using MRI ventilation defect percent (VDP). Ventilation signal intensity voids are estimated using: 1) binary threshold methods, 2) cluster algorithms (k-means, fuzzy c-means, hierarchical-k-means), and, 3) gaussian transformation of the signal intensity histogram with normal to abnormal data comparisons (linear-binning He; Acad Radiol 2014). Unfortunately, these VDP estimation methods have never been directly compared. Hence here we evaluated VDP values using all three methods in MRI acquired in patients with obstructive lung disease. Methods & results: Data acquired under protocol in 116 participants (asthma=90 COPD=26) was evaluated. An automated pipeline (Mozaffaripour; Acad Radiol 2024) was used to estimate VDP. K-means VDP values (Asthma:12±12, COPD:30±19) were significantly greater than linear-binning (Asthma: 6±9, COPD: 8±8, p<.01) and threshold (Asthma:6±7, COPD:11±8, p<.01) values. K-means VDP was correlated with linear-binning (R2=.69, p<.01) and threshold (R2=.85, p<.01) values. Bland-Altman plots revealed wide 95% confidence intervals when comparing k-means with threshold (-3.6%;40.5%) and linear-binning (-5.4%;48.7%) values in COPD and in asthma (threshold: -6.1%;18.8%, linear-binning: -4.8%;15.5%). Significance: Relative to k-means estimates of MRI VDP, linear-binning and thresholding methods significantly underestimated COPD and asthma VDP values. Differences between k-means and the linear-binning and thresholding methods may stem from fixed (versus iterative) thresholds and predefined cluster widths based on healthy volunteer data, which may not identify true zero-signal regions in patients with lung disease.
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 | 0.004 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 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) | 0.003 | 0.001 |
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".