EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Resource-Efficient Hybrid Deep Learning Framework with External Validation for Intracranial Hemorrhage Detection in CT Scans

José Rafael Peña Gutiérrez iD, César Julio Bustacara Medina iD

Diagnostics · 29.08.2026 · 16 (17) · 2776

DOI: 10.3390/diagnostics16172776 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 29.08.2026. Verfasst von José Rafael Peña Gutiérrez und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Systems Engineering, Pontificia Universidad Javeriana, Bogotá 110231, Colombia. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Intracranial hemorrhage (ICH) is a time-critical neurological emergency in which delayed diagnosis significantly worsens patient outcomes. This challenge is amplified in resource-limited, high-workload settings where rapid neuroimaging interpretation may be constrained. Many high-performing deep learning approaches for disease detection rely on large-scale models trained on extensive data and evaluated only on internal datasets, limiting their generalization across heterogeneous clinical environments. This study aims to develop and evaluate a resource-efficient framework for automated ICH detection from CT scans, with internal and external validation across heterogeneous clinical settings.

Methods

A hybrid deep learning framework was developed, combining an EfficientNetV2-S-based feature extractor with a bidirectional GRU model for scan-level prediction. The model was trained on a stratified subset of 6000 CT scans from the RSNA Intracranial Hemorrhage Detection dataset and evaluated using an internal test set and two external validation cohorts (PhysioNet and CQ500).

Results

On an internal held-out test set, the model achieved scan-level AUROC and AUPRC of 0.980 and 0.977, respectively, and slice-level AUROC and AUPRC of 0.981 and 0.923. External validation on the PhysioNet and CQ500 datasets yielded scan-level AUROC/AUPRC values of 0.914/0.932 and 0.905/0.909, respectively, demonstrating consistent performance across datasets differing in institution, geography, patient population, and acquisition protocols.

Conclusions

Despite its compact architecture and reduced training subset, the proposed framework achieves performance competitive with substantially larger and more computationally demanding models, completing training in under 26 h on single-GPU hardware. These results support the feasibility of reproducible, resource-efficient ICH detection systems for automated triage in emergency radiology workflows across different clinical settings.

Schlagwörter

Stichwörter der Autor:innen

clinical decision supportcomputational efficiencycomputed tomographycross-domain generalizationdeep learningintracranial hemorrhagemedical image analysis

Autor:innen und Institutionen

  • Department of Systems Engineering, Pontificia Universidad Javeriana, Bogotá 110231, Colombia.

ORCID-Profile: José Rafael Peña Gutiérrez, César Julio Bustacara Medina

Zitieren

APA

Peña Gutiérrez, J. R., & Bustacara Medina, C. J. (2026). A Resource-Efficient Hybrid Deep Learning Framework with External Validation for Intracranial Hemorrhage Detection in CT Scans. Diagnostics, 16(17), 2776. https://doi.org/10.3390/diagnostics16172776

Vancouver

Peña Gutiérrez JR, Bustacara Medina CJ. A Resource-Efficient Hybrid Deep Learning Framework with External Validation for Intracranial Hemorrhage Detection in CT Scans. Diagnostics. 2026;16(17):2776. doi:10.3390/diagnostics16172776

BibTeX
@article{PeaGutirrez2026,
  author = {Peña Gutiérrez, José Rafael and Bustacara Medina, César Julio},
  title = {A Resource-Efficient Hybrid Deep Learning Framework with External Validation for Intracranial Hemorrhage Detection in CT Scans},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {17},
  pages = {2776},
  doi = {10.3390/diagnostics16172776}
}
Kostenlos starten →