Abstract WMP21: Texture Analysis of Intracranial Thrombus Using CT and CTA Predicts Early Recanalization With Intravenous Alteplase
Bibliographic record
Abstract
Objective: In acute ischemic stroke (AIS), thrombus lysis and early restoration of blood flow to ischemic brain is the goal of reperfusion therapy. We hypothesize that image texture analysis of thrombus using non-contrast CT (NCCT) and CTA can predict early recanalization with IV alteplase in AIS patients with ICA/M1 MCA thrombi. Methods: We used a case control design for the study using the whole cohort of the clinical trial of Identifying New approaches to optimize Thrombus characterization for predicting Early Recanalization and Reperfusion with iv tPA using Serial CT angiography (INTERRSeCT). Cases were 31 patients with ICA/M1 MCA thrombi treated with IV alteplase, who achieved early recanalization (as assessed on first angio run in patients undergoing additional IA therapy or on repeat CTA at 4 hrs). Cases were matched with controls (37 patients with ICA/M1 MCA thrombi treated with IV alteplase who did not achieve recanalization). All patients had thin slice NCCT (slice thickness < 2.5 mm) and CTA (≤ 0.625mm). Thrombi in ICA/M1 MCA region were manually contoured from NCCT guided by co-registered CTA. We extracted 378 features (including thrombus length and volume, first order statistics, and image texture features) from each thrombus in both NCCT and CTA images. This was followed by feature selection using linear discriminative analysis. The top 5 features from NCCT and CTA images along with the clot texture difference between NCCT and CTA were used to train a linear support vector machine classifier. Five times 6-fold cross validation was used to evaluate the trained classifier. Results: Receiver operator curves show that thrombus texture from NCCT and CTA are predictive of early recanalization with IV alteplase. Combined NCCT & CTA features and texture difference is the best predictor (AUC: 0.82). Conclusions: Thrombus texture features from NCCT and CTA are strongly predictive of early recanalization with IV alteplase in AIS patients with proximal occlusions.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| 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 | 0.000 |
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".