Abstract WP45: Algorithm Enhanced Gray-White Matter Non-Contrast CT Improves Reliability of ASPECTS Scoring
Bibliographic record
Abstract
Objective: The Alberta Stroke Program Early CT Score (ASPECTS) is widely used to assess and diagnose acute ischemic stroke (AIS) patients. However, reliability of ASPECTS scoring is poor among physicians with limited expertise. We hypothesize that reliability for ASPECTS scoring can be improved by using algorithm enhanced gray-white matter (AEGWM) NCCT. Methods: Inter-rater reliability for ASPECTS scoring was assessed between plain and AEGWM NCCT by an expert and a novice reader. 50 AIS patient NCCT images were acquired acutely. NCCT images were then enhanced by skull stripping, image smoothing, histogram equalization, and JET color mapping. ASPECTS scoring was done on AEGWM color mapped NCCT and on standard 5mm NCCT images by a novice reader. ASPECTS scoring was done two days apart on standard NCCT first, followed by AEGWM NCCT. Expert (neuro-radiologist) scores on standard NCCT were then compared with scores from the novice reader on both regular and AEGWM NCCT. Results: Agreement between novice and expert for trichotomized ASPECTS (0-4, 5-7, 8-10) was best when the novice was reading ASPECTS on AEGWM NCCT (kappa=0.7093) vs. when novice read ASPECTS on standard NCCT (kappa=0.2409). Difference in scoring the full 10-point ASPECTS score was least when the novice read ASPECTS on AEGWM NCCT (mean ASPECTS difference between novice and expert for algorithm-enhanced NCCT 0.68 ± 1.1 vs. 1.48 ± 1.8 for standard NCCT). A Bland Altman plot comparing the difference is attached and the coefficient of variation was found to be 0.14 for AEGWM NCCT scoring. Conclusion: Algorithm Enhanced Gray-White Matter NCCT allows more accurate/ reliable ASPECTS scoring. Further evaluation on a larger dataset with readers with different levels of expertise is ongoing.
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 | 0.008 | 0.038 |
| 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 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 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".