Acute Infarct Core Volume Estimation on Noncontrast Computed Tomography With a Deep Learning Algorithm
Bibliographic record
Abstract
Background A simplified patient selection paradigm with noncontrast computed tomography (NCCT) can reduce the time to reperfusion and widen the eligibility of acute ischemic stroke large vessel occlusions (LVOs) for endovascular therapy. The objectives of this article are (1) to develop, train, and internally validate a deep learning algorithm that estimates baseline infarct core volume (ICV) on NCCT in anterior circulation LVO patients, and (2) by using an external set, to ascertain how this algorithm's (aICV‐NCCT) predictive performance compares with Alberta Stroke Program Early Computed Tomography Score‐NCCT and ICV‐CT perfusion in its capacity to estimate the final infarct volume established on diffusion‐weighted magnetic resonance imaging at 24‐ to 48‐hour follow‐up. Methods In the first phase, stroke activations with baseline NCCT and CT angiography were used to train an aICV‐NCCT. The algorithm was then internally validated using intraclass correlations and Intersection over Union. In the external set, patients with LVO treated with endovascular therapy achieving modified Thrombolysis in Cerebral Infarction score ≥2b and available baseline NCCT, CT angiography, and CT perfusion were included. Results A total of 2858 studies of patients with stroke alerts were used for training (80%) and internal validation (20%). We obtained a high correlation (intraclass correlation coefficient, 0.78; CI, 0.73–0.83) and an acceptable Intersection over Union of 0.24 on the internal validation set. The external set consisted on 230 patients with an LVO. When predicting final infarct volume on the external set, our aICV‐NCCT was similar to ICV‐CT perfusion (intraclass correlation coefficient, 0.50 versus 0.54; P = 0.764) and Alberta Stroke Program Early Computed Tomography Score‐NCCT (r s , −0.41; P = 0.436). Conclusion In this study, we developed and validated a deep learning algorithm that demonstrates an at least equivalent performance to CT perfusion in estimating core volume on acute stroke imaging studies in patients with suspected anterior circulation LVO strokes. The algorithm's robust performance holds significant potential in settings with limited access to advanced imaging technologies across diverse healthcare environments.
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 | 0.000 |
| 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".