MétaCan
Menu
← Back to cohort

Predicting Acute Ischemic Stroke Core in Multiphase CT Angiography Using a CT Perfusion-Trained Neural Network

2025· article· en· W4416964639 on OpenAlexaff
Thomas D. R. Oldreive, Raneem Sheronick, M. Ethan MacDonald

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldMedicine
TopicAcute Ischemic Stroke Management
Canadian institutionsUniversity of Calgary
Fundersnot available
KeywordsConvolutional neural networkStroke (engine)Artificial neural networkPattern recognition (psychology)Metric (unit)AngiographyCore (optical fiber)Sørensen–Dice coefficientGround truth

Abstract

fetched live from OpenAlex

Early and accurate identification of tissue infarction (stroke core) is crucial for treatment decisions in acute ischemic stroke. While CT angiography (CTA) is widely used and accessible, it lacks standardized methods for core prediction. CT perfusion (CTP) offers improved tissue classification but is limited by higher cost and complexity. This study aims to bridge this gap by developing a convolutional neural network (CNN) trained on CTP core maps to differentiate ischemic core from healthy tissue in multiphase CTA (mCTA) images. We retrospectively analyzed acute ischemic stroke patients who underwent both CTP and mCTA (n=99). Two additional datasets with increasing stroke severity - Severe15 and Severe20 - were derived from the base dataset to assess model performance across a range of clinical scenarios (n=58 and n=31, respectively). The CNN was trained using CTP-derived core maps as ground truth and applied to mCTA-based feature maps. Model performance was optimized using cross-entropy loss and evaluated with thresholding analysis. The primary metric was the Dice similarity coefficient (DSC), supplemented by various thresholded accuracy metrics and threshold-independent precision-recall curve analysis. The model trained on the base dataset demonstrated reasonable performance in distinguishing ischemic stroke core from healthy tissue, achieving a DSC of 0.43. As stroke severity increased, thresholded accuracy metrics improved or remained consistent, with the Severe20 model achieving a DSC of 0.60. Precision-recall curve analysis further highlighted the tradeoff between DSC and overall model precision. This study demonstrates the potential of leveraging machine learning to enhance stroke imaging accessibility by integrating the core detection capabilities of CTP with the speed and availability of CTA. Future work will focus on optimizing performance for clinical translation and expanding validation to larger datasets.Clinical Relevance-- The model developed in this study provides a starting point for a reliable, data-driven approach to stroke imaging that can enhance equitable access to advanced diagnostics and support more informed clinical decision-making, especially in severe stroke cases.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.011
Threshold uncertainty score0.022

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.018
GPT teacher head0.291
Teacher spread0.272 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicAcute Ischemic Stroke Management→French-language works237,207→