Automated Identification of Thrombectomy Amenable Vessel Occlusion on Computed Tomography Angiography using Deep Learning
Bibliographic record
Abstract
Abstract Objectives Recent advancements have extended the treatment window for large vessel occlusion in acute ischemic stroke, prompting a shift in the standard of care for patients presenting within 6 to 24 hours. We developed and externally validated an automated deep learning algorithm for detecting thrombectomy amenable vessel occlusion (TAVO) in computed tomography angiography (CTA). Methods The algorithm was trained on 2,045 acute ischemic stroke patients who underwent CTA, and validation was conducted using two external datasets comprising 64 (external 1) and 313 (external 2) patients with ischemic stroke. TAVO was defined as occlusion in the intracranial internal carotid artery (ICA), or M1/M2 segment of the middle cerebral artery (MCA). Utilizing U-Net for vessel segmentation and EfficientNetV2 for TAVO prediction, the algorithm’s diagnostic performance was assessed using the area under the receiver operating characteristics curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Results The mean age in the training and validation dataset was 68.7±12.6; 56.3% were men, and 18.0% had TAVO. The algorithm achieved AUC of 0.950 (95% CI, 0.915–0.971) in the internal test. For the external datasets 1 and 2, the AUCs were 0.970 (0.897–0.997) and 0.971 (0.924–0.990), respectively. Notably, the algorithm demonstrated robust sensitivity and specificity (approximately 0.95) for intracranial ICA or M1-MCA occlusion, but a slight reduction in performance for isolated M2-MCA occlusion. Conclusion This validated algorithm has potential applications in identifying TAVO and could aid less-experienced clinicians, potentially expediting the treatment process for eligible patients.
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 | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".