Automated Quantification of Stroke Damage on Brain Computed Tomography Scans: e-ASPECTS
Bibliographic record
Abstract
Emergency radiological diagnosis of acute ischaemic stroke requires the accurate detection and appropriate interpretation of relevant imaging findings. Non-contrast computed tomography (CT) provides fast and low-cost assessment of the early signs of ischaemia and is the most widely used diagnostic modality for acute stroke. The Alberta Stroke Program Early CT Score (ASPECTS) is a quantitative and clinically validated method to measure the extent of ischaemic signs on brain CT scans. The CE-marked electronic-ASPECTS (e-ASPECTS) software automates the ASPECTS score. Anglia Ruskin Clinical Trials Unit (ARCTU) independently carried out a clinical investigation of the e-ASPECTS software, an automated scoring system which can be integrated into the diagnostic pathway of an acute ischaemic stroke patient, thereby assisting the physician with expert interpretation of the brain CT scan. Here we describe a literature review of the clinical importance of reliable assessment of early ischaemic signs on plain CT scans, and of technologies automating these processed scoring systems in ischaemic stroke on CT scans focusing on the e-ASPECTS software. To be suitable for critical appraisal in this evaluation, the published studies needed a sample size of a minimum of 10 cases. All randomised studies were screened and data deemed relevant to demonstration of performance of ASPECTS were appraised. The literature review focused on three domains: i) interpretation of brain CT scans of stroke patients, ii) the application of the ASPECTS score in ischaemic stroke, and iii) automation of brain CT analysis. Finally, the appraised references are discussed in the context of the clinical impact of e-ASPECTS and the expected performance, which will be independently evaluated by a non-inferiority study conducted by the ARCTU.
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 | 0.009 | 0.036 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.011 | 0.007 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".