Detection of Cerebral Ischaemia using Transfer Learning Techniques

Antón-Munárriz, Cristina, Pastor-Vargas, Rafael, Haut, Juan M., Robles-Gómez, Antonio, Paoletti, Mercedes E. y Benítez-Andrades, José A.() .Detection of Cerebral Ischaemia using Transfer Learning Techniques. 36th International Symposium on Computer-Based Medical Systems (CBMS).En: L'Aquila, Italy. (2023-06-22)

Ficheros (Some files may be inaccessible until you login with your e-spacio credentials)
Nombre Descripción Tipo MIME Size
Robles_Gomez_Antonio-Detection-of-cerebral-ischeamia.pdf Robles_Gomez_Antonio-Detection-of-cerebral-ischeamia.pdf application/pdf 412.96KB

Título de la Conferencia 36th International Symposium on Computer-Based Medical Systems (CBMS)
Fecha de inicio de la Conferencia 2023-06-22
Fecha fín de la Conferencia 2023-06-24
Lugar de la Conferencia L'Aquila, Italy
Numeros de las páginas 589-594
Titulo Detection of Cerebral Ischaemia using Transfer Learning Techniques
Autor(es) Antón-Munárriz, Cristina
Pastor-Vargas, Rafael
Haut, Juan M.
Robles-Gómez, Antonio
Paoletti, Mercedes E.
Benítez-Andrades, José A.
Notas adicionales ISBN 979-8-3503-1224-9
Materia(s) Ingeniería Informática
Abstract Cerebrovascular accident (CVA) or stroke is one of the main causes of mortality and morbidity today, causing permanent disabilities. Its early detection helps reduce its effects and its mortality: time is brain. Currently, non-contrast computed tomography (NCCT) continues to be the first-line diagnostic method in stroke emergencies because it is a fast, available, and cost-effective technique that makes it possible to rule out haemorrhage and focus attention on the ischemic origin, that is, due to obstruction to arterial flow. NCCT are quantified using a scoring system called ASPECTS (Alberta Stroke Program Early Computed Tomography Score) according to the affected brain structures. This paper aims to detect in an initial phase those CTs of patients with stroke symptoms that present early alterations in CT density using a binary classifier of CTs without and with stroke, to alert the doctor of their existence. For this, several well-known neural network architectures are implemented in the ImageNet challenges (VGG, NasNet, ResNet and DenseNet), with 3D images, covering the entire brain volume. The training results of these networks are exposed, in which different parameters are tested to obtain maximum performance, which is achieved with a DenseNet3D network that achieves an accuracy of 98% in the training set and 95% in the test set
Palabra clave Cerebral Ischaemia
Computed tomography
Deep Learning
Transfer Learning
Ictus Dataset
Editor(es) IEEE
Formato application/pdf
Identificador bibliuned:DptoSCC-ETSI-Ponencias-Arobles
http://e-spacio.uned.es/fez/view/bibliuned:DptoSCC-ETSI-Ponencias-Arobles
https://doi.org/10.1109/CBMS58004.2023.00284
Idioma eng
Versión de la publicación acceptedVersion
Nivel de acceso y licencia http://creativecommons.org/licenses/by-nc-nd/4.0
Tipo de recurso conferenceObject
Tipo de acceso Acceso embargado

 
Versiones
Versión Tipo de filtro
Contador de citas: Google Scholar Search Google Scholar
Estadísticas de acceso: 123 Visitas, 14 Descargas  -  Estadísticas en detalle
Creado: Fri, 19 Jan 2024, 05:15:37 CET