D
Daniela S. Mantilla
Researcher at El Bosque University
Publications - 5
Citations - 9
Daniela S. Mantilla is an academic researcher from El Bosque University. The author has contributed to research in topics: Computer science & Medicine. The author has co-authored 1 publications.
Papers
More filters
Journal ArticleDOI
Utility of biomarkers in traumatic brain injury: a narrative review
Daniel A. Mendoza,Karen D. López,Raul A. Echeverri,Laura Pastor,Steven Rueda,Laura Fernandez,Daniela S. Mantilla,María F. Díaz,María C. Ramírez,Diana C. Barragán,Andres M. Rubiano +10 more
TL;DR: This narrative review is intended to discuss the state of the art of the most frequently used biomarkers in TBI, their clinical utility, and the implications for therapeutic decisionmaking protocols.
Proceedings ArticleDOI
A deep CT to MRI unpaired translation that preserve ischemic stroke lesions
TL;DR: This work introduces a deep generative strategy that allows ischemic stroke lesion translation over synthetic DWI-MRI images, including U-net modules, hierarchically organized, with inter-level connections that preserve brain structures, while codifying an embedding representation.
Journal ArticleDOI
Deep learning representations to support COVID-19 diagnosis on CT slices
Josué Ruano,J.C.S. Arcila,David Romo-Bucheli,Carlos Vargas,Jefferson Rodriguez,Óscar Mendoza,Miguel Plazas,Lola Bautista,Jorge Villamizar,Gabriel Pedraza,A. Moreno,Diana Valenzuela,Lina Vásquez,C. Valenzuela-Santos,Paúl Camacho,Daniela S. Mantilla,Fabio Martínez +16 more
TL;DR: Deep representations have achieved outstanding performance in the identification of CO VID-19 cases on CT scans demonstrating good characterization of the COVID-19 radiological patterns, which could potentially support the COvid-19 diagnosis in clinical settings.
Proceedings ArticleDOI
An attentional unet with an auxiliary class learning to support acute ischemic stroke segmentation on CT
Santiago Gómez,Sebastian Florez,Daniela S. Mantilla,Paúl Camacho,Nick Tarazona,Fabio Martínez +5 more
TL;DR: In this paper , a boundary-focused attention U-Net is proposed to recover stroke segmentation on CT scans, enriched with skip connections, which help in recovering of saliency lesion maps and motivated the preservation of morphology.
Journal ArticleDOI
A deep supervised cross-attention strategy for ischemic stroke segmentation in MRI studies
Santiago Gómez,Daniela S. Mantilla,Edgar Roman Rangel,Andrés F Ortiz,D. D Vera,Fabio Martínez +5 more
TL;DR: In this article , a cross-attention deep autoencoder was proposed for the localization and delineation of brain lesion from MRI images, which can better support the discrimination between healthy and lesion regions, which results in favorable prognosis and follow-up of patients.