EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Deep Learning in Emergency Radiology: Evaluating a Tool for Automated ASPECT Scoring in Acute Ischemic Stroke

Julia G. O'Connor, Angela Ayobi, Maxime Tassy, Christophe Avare, Sarah Quenet, Adam Davis, Peter D. Chang, Daniel S. Chow, Christopher G. Filippi, Yasmina Chaibi

Clinical Neuroimaging · 2025-01 · 2 (1)

DOI: 10.1002/neo2.70034 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Clinical Neuroimaging, online erschienen am 06.09.2025. Verfasst von Julia G. O'Connor und 9 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and Purpose The Alberta Stroke Program Early Computed Tomography Score (ASPECTS) quantifies ischemic damage in middle cerebral artery territory strokes, guiding treatment decisions including thrombolysis and mechanical thrombectomy. However, inter‐rater variability in scoring limits its clinical reliability. Automated ASPECTS tools like CINA‐ASPECTS (v1.4.3, Avicenna.AI) have shown potential to enhance consistency and efficiency. This study validated CINA‐ASPECTS using a multinational, multi‐scanner external dataset against a ground truth (GT) established by expert neuroradiologists.

Methods

Head NCCT scans from 339 patients (20 ASPECTS regions each) were collected from clinical sites in the United States, France, and Japan. Five US board‐certified expert neuroradiologists participated in establishing the GT using NCCT and additional imaging when available, blinded to each other and the device output. CINA‐ASPECTS outputs were compared to this GT on a region‐based and score‐based level. Stratified analyses were conducted by scanner manufacturer, cortical versus deep regions, and individual ASPECTS regions.

Results

CINA‐ASPECTS demonstrated 72.8% sensitivity, 91.8% specificity, and an area under the receiver operating characteristic curve of 0.823 in region‐based analysis. Score‐based agreement showed an intraclass correlation coefficient (ICC) of 0.83 [95% CI: 0.79–0.86]. Dichotomized score‐based analysis showed good specificity, sensitivity, and ICC. Stratified analysis confirmed consistent performance across scanner manufacturers and cortical/deep ASPECTS regions. Performance was robust regardless of ASPECTS region, potentially aiding in the scoring of difficult regions.

Conclusions

CINA‐ASPECTS reliably identifies ischemic changes across diverse clinical and imaging conditions, achieving good agreement with expert consensus. These findings support its utility in clinical decision‐making for acute stroke management.

Zitieren

APA

O'Connor, J. G., Ayobi, A., Tassy, M., Avare, C., Quenet, S., Davis, A., Chang, P. D., Chow, D. S., Filippi, C. G., & Chaibi, Y. (2025). Deep Learning in Emergency Radiology: Evaluating a Tool for Automated ASPECT Scoring in Acute Ischemic Stroke. Clinical Neuroimaging, 2(1). https://doi.org/10.1002/neo2.70034

Vancouver

O'Connor JG, Ayobi A, Tassy M, Avare C, Quenet S, Davis A, et al. Deep Learning in Emergency Radiology: Evaluating a Tool for Automated ASPECT Scoring in Acute Ischemic Stroke. Clinical Neuroimaging. 2025;2(1). doi:10.1002/neo2.70034

BibTeX
@article{OConnor2025,
  author = {O'Connor, Julia G. and Ayobi, Angela and Tassy, Maxime and Avare, Christophe and Quenet, Sarah and Davis, Adam and Chang, Peter D. and Chow, Daniel S. and Filippi, Christopher G. and Chaibi, Yasmina},
  title = {Deep Learning in Emergency Radiology: Evaluating a Tool for Automated ASPECT Scoring in Acute Ischemic Stroke},
  journal = {Clinical Neuroimaging},
  year = {2025},
  volume = {2},
  number = {1},
  doi = {10.1002/neo2.70034}
}
Kostenlos starten →