Pastor Vargas, RafaelAntón‑Munárriz, CristinaHaut, Juan M.Robles Gómez, AntonioPaoletti, Mercedes E.Benítez Andrades, José Alberto2025-05-262025-05-262025-05-20Pastor-Vargas, R., Antón-Munárriz, C., Haut, J.M., Robles- Gómez, A., Paoletti, M.E., Benítez-Andrades, J.A. (2025); Cerebral ischemia detection using deep learning techniques; Health Information Science and Systems, vol. 13, nº 36, Springer International Publishing ; Páginas 1-19; (https://doi.org/10.1007/s13755-025-00352-8).2047-2501https://doi.org/10.1007/s13755-025-00352-8https://hdl.handle.net/20.500.14468/26841La versión registrada de este artículo, publicado por primera vez en Health Information Science and Systems, vol. 13, nº 36, está disponible en línea en el sitio web del editor: Springer International Publishing, https://doi.org/10.1007/s13755-025-00352-8. The registered version of this article, first published in Health Information Science and Systems, Vol. 13, No. 36, is available online from the publisher's website: Springer International Publishing, https://doi.org/10.1007/s13755-025-00352-8.Cerebrovascular accident (CVA), commonly known as stroke, stands as a significant contributor to contemporary mortality and morbidity rates, often leading to lasting disabilities. Early identification is crucial in mitigating its impact and reducing mortality. Non-contrast computed tomography (NCCT) remains the primary diagnostic tool in stroke emergencies due to its speed, accessibility, and cost-effectiveness. NCCT enables the exclusion of hemorrhage and directs attention to ischemic causes resulting from arterial flow obstruction. Quantification of NCCT findings employs the Alberta Stroke Program Early Computed Tomography Score (ASPECTS), which evaluates affected brain structures. This study seeks to identify early alterations in NCCT density in patients with stroke symptoms using a binary classifier distinguishing NCCT scans with and without stroke. To achieve this, various well-known deep learning architectures, namely VGG3D, ResNet3D, and DenseNet3D, validated in the ImageNet challenges, are implemented with 3D images covering the entire brain volume. The training results of these networks are presented, wherein diverse parameters are examined for optimal performance. The DenseNet3D network emerges as the most effective model, attaining a training set accuracy of 98% and a test set accuracy of 95%. The aim is to alert medical professionals to potential stroke cases in their early stages based on NCCT findings displaying altered density patterns.eninfo:eu-repo/semantics/openAccess1203.17 InformáticaartículoCerebral ischemiaComputed tomographyDeep learningTransfer learningIctus dataset