EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning Applied to Intracranial Hemorrhage Detection

Luis Cortés-Ferre iD, Miguel Angel Gutiérrez-Naranjo iD, Juan José Egea-Guerrero iD, Soledad Pérez-Sánchez iD, Marcin Balcerzyk iD

Journal of Imaging · 07.02.2023 · 9 (2) · 37

DOI: 10.3390/jimaging9020037 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 07.02.2023. Verfasst von Luis Cortés-Ferre und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Sciences and Artificial Intelligence, University of Seville, Avda. Reina Mercedes s/n, 41012 Sevilla, Spain. Die Arbeit wurde bisher 58-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministerio de Ciencia e Innovación of Spain, Fundación ¨la Caixa", Consejería de Igualdad, Salud 435 y Políticas Sociales de Andalucía, Spain.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intracranial hemorrhage is a serious medical problem that requires rapid and often intensive medical care. Identifying the location and type of any hemorrhage present is a critical step in the treatment of the patient. Detection of, and diagnosis of, a hemorrhage that requires an urgent procedure is a difficult and time-consuming process for human experts. In this paper, we propose methods based on EfficientDet’s deep-learning technology that can be applied to the diagnosis of hemorrhages at a patient level and which could, thus, become a decision-support system. Our proposal is two-fold. On the one hand, the proposed technique classifies slices of computed tomography scans for the presence of hemorrhage or its lack of, and evaluates whether the patient is positive in terms of hemorrhage, and achieving, in this regard, 92.7% accuracy and 0.978 ROC AUC. On the other hand, our methodology provides visual explanations of the chosen classification using the Grad-CAM methodology.

Schlagwörter

Stichwörter der Autor:innen

decision support systemdeep learningimage detectionintracranial hemorrhage

Autor:innen und Institutionen

  • Department of Computer Sciences and Artificial Intelligence, University of Seville, Avda. Reina Mercedes s/n, 41012 Sevilla, Spain.
  • Hospital Universitario Virgen del Rocio, Avda. Manuel Siurot, 41013 Sevilla, Spain.
  • Instituto de Biomedicina de Sevilla (Universidad de Sevilla-CSIC-Junta de Andalucía), 41013 Sevilla, Spain.
  • Stroke Unit, Neurology Department, Hospital Universitario Virgen Macarena, 41009 Sevilla, Spain.
  • Neurovascular Research Laboratory, Instituto de Biomedicina de Sevilla-IBiS, 41013 Seville, Spain.
  • Department of Medical Physiology and Biophysics, University of Seville, 41009 Sevilla, Spain.

ORCID-Profile: Luis Cortés-Ferre, Miguel Angel Gutiérrez-Naranjo, Juan José Egea-Guerrero, Soledad Pérez-Sánchez, Marcin Balcerzyk

Förderung

  • Ministerio de Ciencia e Innovación of Spain
  • Fundación ¨la Caixa"
  • Consejería de Igualdad, Salud 435 y Políticas Sociales de Andalucía, Spain
  • European Commission
  • “la Caixa” Foundation
  • Consejería de Igualdad, Salud y Políticas Sociales de Andalucía, Spain

Zitieren

APA

Cortés-Ferre, L., Gutiérrez-Naranjo, M. A., Egea-Guerrero, J. J., Pérez-Sánchez, S., & Balcerzyk, M. (2023). Deep Learning Applied to Intracranial Hemorrhage Detection. Journal of Imaging, 9(2), 37. https://doi.org/10.3390/jimaging9020037

Vancouver

Cortés-Ferre L, Gutiérrez-Naranjo MA, Egea-Guerrero JJ, Pérez-Sánchez S, Balcerzyk M. Deep Learning Applied to Intracranial Hemorrhage Detection. Journal of Imaging. 2023;9(2):37. doi:10.3390/jimaging9020037

BibTeX
@article{CortsFerre2023,
  author = {Cortés-Ferre, Luis and Gutiérrez-Naranjo, Miguel Angel and Egea-Guerrero, Juan José and Pérez-Sánchez, Soledad and Balcerzyk, Marcin},
  title = {Deep Learning Applied to Intracranial Hemorrhage Detection},
  journal = {Journal of Imaging},
  year = {2023},
  volume = {9},
  number = {2},
  pages = {37},
  doi = {10.3390/jimaging9020037}
}
Kostenlos starten →