Abstract WP108: A Novel Multiphase CTA Perfusion Tool Compared To CTP In Patients With Suspected Acute Ischemic Stroke
Bibliographic record
Abstract
Introduction: We recently published a Machine Learning-based algorithm using mCTA (mCTAp) that generates perfusion maps of the brain, similar to CTP. Here, we aim to validate the clinical utility of mCTAp in detection of ischemia, it’s side, extent and location. Methods: One hundred and twenty-one subjects were included in the test dataset. These subjects had completed mCTAp (StrokeSENS) and CTP (4D; GE Healthcare) at baseline. After excluding 2/121 subjects due to poor image quality, a multi-reader-multi-case (n=119) study design was conducted with 3 experienced radiologists, reading post-processed maps (Tmax and rCBF) generated by both mCTAp and CTP. Both reading sessions were separated by a few days. All readers were blinded to modality and clinical information and the reading order was randomized between sessions. Core lab imaging assessments that used NCCT, mCTA and CTP were considered as ground truth. A mixed effect regression model with the reader as random effect variable was used to calculate the AUC, sensitivity, and specificity for both imaging arms regarding ischemia detection, ischemia side, and occlusion site selection (i.e., ICA/M1[considered LVO], M2 or distal, ACA or PCA). The time required for image interpretation was compared between the two modalities. Results: The AUCs for detecting ischemia were comparable between mCTAp and CTP (0.85 [95%CI:0.8-0.9] and 0.84 [95%CI:0.8-0.9] respectively; p=0.43), the affected ischemic side (0.94 [0.92-0.97] and 0.96 [0.94-0.98] respectively; p=0.69), detecting a LVO (0.84 [0.8-0.9] and 0.86 [0.8-0.9]; p=0.31) and M2 or distal occlusions (0.8 [0.7-0.8] and 0.9 [0.84-0.92]; p=0.22). The median (IQR) time for interpretation was 62s (46-78) and 59s (42-69) for mCTAp and CTP respectively (p=0.15). Conclusion: mCTAp shows similar performances when compared to CTP in assisting readers to detect ischemia, location, and extent by using Tmax and rCBF perfusion maps.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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".