Mostrar el registro sencillo del ítem

dc.contributor.authorNogueira Rodríguez, Alba
dc.contributor.authorDOMINGUEZ CARBAJALES, RUBEN 
dc.contributor.authorCampos-Tato, F.
dc.contributor.authorHerrero Rivas, Jesús Miguel
dc.contributor.authorPuga Gimenez de Azcárate, Manuel 
dc.contributor.authorRemedios Espino, David Rafael 
dc.contributor.authorRivas Moral, Laura 
dc.contributor.authorSánchez Hernández, Eloy 
dc.contributor.authorIglesias Gómez, Agueda
dc.contributor.authorCubiella Fernández, Joaquín 
dc.contributor.authorFernández Riverola, Florentino
dc.contributor.authorLopez-Fernandez, H.
dc.contributor.authorReboiro Jato, Miguel
dc.contributor.authorGonzález Pena, Daniel
dc.date.accessioned2024-01-02T10:05:07Z
dc.date.available2024-01-02T10:05:07Z
dc.date.issued2021
dc.identifier.issn0941-0643
dc.identifier.urihttp://hdl.handle.net/20.500.11940/18531
dc.description.abstractColorectal cancer is a major health problem, where advances towards computer-aided diagnosis (CAD) systems to assist the endoscopist can be a promising path to improvement. Here, a deep learning model for real-time polyp detection based on a pre-trained YOLOv3 (You Only Look Once) architecture and complemented with a post-processing step based on an object-tracking algorithm to reduce false positives is reported. The base YOLOv3 network was fine-tuned using a dataset composed of 28,576 images labelled with locations of 941 polyps that will be made public soon. In a frame-based evaluation using isolated images containing polyps, a general F-1 score of 0.88 was achieved (recall = 0.87, precision = 0.89), with lower predictive performance in flat polyps, but higher for sessile, and pedunculated morphologies, as well as with the usage of narrow band imaging, whereas polyp size < 5 mm does not seem to have significant impact. In a polyp-based evaluation using polyp and normal mucosa videos, with a positive criterion defined as the presence of at least one 50-frames-length (window size) segment with a ratio of 75% of frames with predicted bounding boxes (frames positivity), 72.61% of sensitivity (95% CI 68.99-75.95) and 83.04% of specificity (95% CI 76.70-87.92) were achieved (Youden = 0.55, diagnostic odds ratio (DOR) = 12.98). When the positive criterion is less stringent (window size = 25, frames positivity = 50%), sensitivity reaches around 90% (sensitivity = 89.91%, 95% CI 87.20-91.94; specificity = 54.97%, 95% CI 47.49-62.24; Youden = 0.45; DOR = 10.76). The object-tracking algorithm has demonstrated a significant improvement in specificity whereas maintaining sensitivity, as well as a marginal impact on computational performance. These results suggest that the model could be effectively integrated into a CAD system.
dc.language.isoen
dc.rightsAtribución 4.0 Internacional
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.titleReal-time polyp detection model using convolutional neural networks
dc.typeJournal Articlees
dc.authorsophosNogueira-Rodriguez, A.;Dominguez-Carbajales, R.;Campos-Tato, F.;Herrero, J.;Puga, M.;Remedios, D.;Rivas, L.;Sanchez, E.;Iglesias, A.;Cubiella, J.;Fdez-Riverola, F.;Lopez-Fernandez, H.;Reboiro-Jato, M.;Glez-Pena, D.
dc.identifier.doi10.1007/s00521-021-06496-4
dc.identifier.sophos46937
dc.issue.number0
dc.journal.titleNEURAL COMPUTING & APPLICATIONS
dc.organizationServizo Galego de Saúde::Áreas Sanitarias (A.S.)::Área Sanitaria de Ourense, Verín e O Barco de Valdeorras - Complexo Hospitalario Universitario de Ourense::Dixestivo||Servizo Galego de Saúde::Áreas Sanitarias (A.S.)::Área Sanitaria de Ourense, Verín e O Barco de Valdeorras - Complexo Hospitalario Universitario de Ourense::Informática
dc.relation.publisherversionhttps://link.springer.com/content/pdf/10.1007/s00521-021-06496-4.pdfes
dc.rights.accessRightsopenAccess
dc.subject.keywordCHUOes
dc.typefidesArtículo Científico (incluye Original, Original breve, Revisión Sistemática y Meta-análisis)es
dc.typesophosArtículo Originales
dc.volume.number0


Ficheros en el ítem

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem

Atribución 4.0 Internacional
Excepto si se señala otra cosa, la licencia del ítem se describe como Atribución 4.0 Internacional