Mostrar el registro sencillo del ítem
dc.contributor.author
Mosquera, Candelaria.
dc.contributor.author
Diaz, Facundo Nahuel
dc.contributor.author
Binder, Fernando
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.contributor.author
Ravellino, José Martin
dc.contributor.author
Benítez, Sonia Bibiana
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.contributor.author
Beresñak, Alejandro
dc.contributor.author
Seehaus, Alberto
dc.contributor.author
Ducrey, Gabriel
dc.contributor.author
Ocantos, Jorge A.
dc.contributor.author
Luna, Daniel Roberto
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.date.available
2021-12-14T12:44:10Z
dc.date.issued
2021-07
dc.identifier.citation
Mosquera, Candelaria.; Diaz, Facundo Nahuel; Binder, Fernando; Ravellino, José Martin; Benítez, Sonia Bibiana; et al.; Chest x-ray automated triage: A semiologic approach designed for clinical implementation, exploiting different types of labels through a combination of four Deep Learning architectures; Elsevier Ireland; Computer Methods And Programs In Biomedicine; 206; 7-2021; 1-20
dc.identifier.issn
0169-2607
dc.identifier.uri
http://hdl.handle.net/11336/148691
dc.description.abstract
Background and objectives: The multiple chest x-ray datasets released in the last years have ground-truth labels intended for different computer vision tasks, suggesting that performance in automated chest x-ray interpretation might improve by using a method that can exploit diverse types of annotations. This work presents a Deep Learning method based on the late fusion of different convolutional architectures, that allows training with heterogeneous data with a simple implementation, and evaluates its performance on independent test data. We focused on obtaining a clinically useful tool that could be successfully integrated into a hospital workflow. Materials and methods: Based on expert opinion, we selected four target chest x-ray findings, namely lung opacities, fractures, pneumothorax and pleural effusion. For each finding we defined the most suitable type of ground-truth label, and built four training datasets combining images from public chest x-ray datasets and our institutional archive. We trained four different Deep Learning architectures and combined their outputs with a late fusion strategy, obtaining a unified tool. The performance was measured on two test datasets: an external openly-available dataset, and a retrospective institutional dataset, to estimate performance on the local population. Results: The external and local test sets had 4376 and 1064 images, respectively, for which the model showed an area under the Receiver Operating Characteristics curve of 0.75 (95%CI: 0.74–0.76) and 0.87 (95%CI: 0.86–0.89) in the detection of abnormal chest x-rays. For the local population, a sensitivity of 86% (95%CI: 84–90), and a specificity of 88% (95%CI: 86–90) were obtained, with no significant differences between demographic subgroups. We present examples of heatmaps to show the accomplished level of interpretability, examining true and false positives. Conclusion: This study presents a new approach for exploiting heterogeneous labels from different chest x-ray datasets, by choosing Deep Learning architectures according to the radiological characteristics of each pathological finding. We estimated the tool's performance on the local population, obtaining results comparable to state-of-the-art metrics. We believe this approach is closer to the actual reading process of chest x-rays by professionals, and therefore more likely to be successful in a real clinical setting.
dc.format
application/pdf
dc.language.iso
eng
dc.publisher
Elsevier Ireland
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.rights
info:eu-repo/semantics/restrictedAccess
dc.rights.uri
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.subject
ARTIFICIAL INTELLIGENCE
dc.subject
CHEST
dc.subject
CLINICAL DECISION SUPPORT SYSTEMS
dc.subject
DEEP LEARNING
dc.subject
RADIOGRAPHY
dc.subject.classification
Otras Ciencias de la Salud
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.subject.classification
Ciencias de la Salud
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.subject.classification
CIENCIAS MÉDICAS Y DE LA SALUD
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.title
Chest x-ray automated triage: A semiologic approach designed for clinical implementation, exploiting different types of labels through a combination of four Deep Learning architectures
dc.type
info:eu-repo/semantics/article
dc.type
info:ar-repo/semantics/artículo
dc.type
info:eu-repo/semantics/publishedVersion
dc.date.updated
2021-12-03T20:40:50Z
dc.journal.volume
206
dc.journal.pagination
1-20
dc.journal.pais
Irlanda
dc.journal.ciudad
Amsterdam
dc.description.fil
Fil: Mosquera, Candelaria.. Universidad Tecnológica Nacional; Argentina. Hospital Italiano; Argentina
dc.description.fil
Fil: Diaz, Facundo Nahuel. Hospital Italiano; Argentina
dc.description.fil
Fil: Binder, Fernando. Hospital Italiano; Argentina
dc.description.fil
Fil: Ravellino, José Martin. Hospital Italiano; Argentina
dc.description.fil
Fil: Benítez, Sonia Bibiana. Hospital Italiano; Argentina
dc.description.fil
Fil: Beresñak, Alejandro. Hospital Italiano; Argentina
dc.description.fil
Fil: Seehaus, Alberto. Hospital Italiano; Argentina
dc.description.fil
Fil: Ducrey, Gabriel. Hospital Italiano; Argentina
dc.description.fil
Fil: Ocantos, Jorge A.. Hospital Italiano; Argentina
dc.description.fil
Fil: Luna, Daniel Roberto. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Houssay. Instituto de Medicina Traslacional e Ingeniería Biomédica - Hospital Italiano. Instituto de Medicina Traslacional e Ingeniería Biomédica.- Instituto Universitario Hospital Italiano de Buenos Aires. Instituto de Medicina Traslacional e Ingeniería Biomédica; Argentina
dc.journal.title
Computer Methods And Programs In Biomedicine
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/abs/pii/S0169260721002054?via%3Dihub
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1016/j.cmpb.2021.106130
Archivos asociados