Abstract WMP23: Automated Regional Density Measurements on Baseline Non-Contrast CT Predict Final Infarction in Acute Ischemic Stroke Patients
Bibliographic record
Abstract
Introduction: Early ischemic changes on non-contrast CT (NCCT) can be visually assessed using the Alberta Stroke Program Early CT Score (ASPECTS). We sought to determine if automated regional density quantification provides additional information on the development of final infarction. Methods: We selected 121 patients with middle cerebral artery stroke due to large vessel occlusion out of a consecutive cohort. Densities in ASPECTS regions were quantified as average Hounsfield Unit (HU) values using automated segmentation (Fig. 1). Relative HU (rHU) values were calculated dividing absolute regional densities of ischemic by non-ischemic hemispheres. Final infarction was quantified semi-automatically as total volume and was defined visually per ASPECTS region in a dichotomized fashion. A composite rHU score incorporating values from all ASPECTS regions weighted by regional relevance was calculated. ROC analysis was performed to calculate AUC values. Linear regression analysis was used for multivariable adjustment. Results: Median visual ASPECTS on NCCT was 8 (IQR: 6-9). Automated density measurements were feasible in all 121 patients within one minute of post-processing time. rHU values yielded significant regional classification of final infarction in ROC analyses for all ASPECTS regions except M3 and M6. Best classifications were achieved for lentiform nucleus (AUC=0.810, p<0.001), caudate nucleus (AUC=0.777, p<0.001), and insula (AUC=0.764, p<0.001). The composite rHU score was independently associated with final infarction volume (β=-0.353, p<0.001), outperforming visual ASPECTS assessment (β=-0.190, p=0.062) in multivariable regression analysis. Conclusions: Automated NCCT density changes identify ASPECTS regions that develop final infarction in stroke patients. The composite rHU score outperformed visual ASPECTS interpretation in the prediction of final infarction volumes and may serve as an observer-independent imaging biomarker.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 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 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".