Mostrar el registro sencillo del ítem
dc.contributor.author
Monteiro, Miguel
dc.contributor.author
Newcombe, Virginia F J
dc.contributor.author
Mathieu, Francois
dc.contributor.author
Adatia, Krishma
dc.contributor.author
Kamnitsas, Konstantinos
dc.contributor.author
Ferrante, Enzo
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.contributor.author
Das, Tilak
dc.contributor.author
Whitehouse, Daniel
dc.contributor.author
Rueckert, Daniel
dc.contributor.author
Menon, David K
dc.contributor.author
Glocker, Ben
dc.date.available
2020-07-06T16:51:17Z
dc.date.issued
2020-05
dc.identifier.citation
Monteiro, Miguel; Newcombe, Virginia F J; Mathieu, Francois; Adatia, Krishma; Kamnitsas, Konstantinos; et al.; Multiclass semantic segmentation and quantification of traumatic brain injury lesions on head CT using deep learning: an algorithm development and multicentre validation study; Elsevier; The Lancet Digital Health; 2; 5-2020; 1-9
dc.identifier.issn
2589-7500
dc.identifier.uri
http://hdl.handle.net/11336/108905
dc.description.abstract
Background. CT is the most common imaging modality in traumatic brain injury (TBI). However, its conventional use requires expert clinical interpretation and does not provide detailed quantitative outputs, which may have prognostic importance. We aimed to use deep learning to reliably and efficiently quantify and detect different lesion types.Methods. Patients were recruited between Dec 9, 2014, and Dec 17, 2017, in 60 centres across Europe. We trained and validated an initial convolutional neural network (CNN) on expert manual segmentations (dataset 1). This CNN was used to automatically segment a new dataset of scans, which we then corrected manually (dataset 2). From this dataset, we used a subset of scans to train a final CNN for multiclass, voxel-wise segmentation of lesion types. The performance of this CNN was evaluated on a test subset. Performance was measured for lesion volume quantification, lesion progression, and lesion detection and lesion volume classification. For lesion detection, external validation was done on an independent set of 500 patients from India.Findings98 scans from one centre were included in dataset 1. Dataset 2 comprised 839 scans from 38 centres: 184 scans were used in the training subset and 655 in the test subset. Compared with manual reference, CNN-derived lesion volumes showed a mean difference of 0·86 mL (95% CI −5·23 to 6·94) for intraparenchymal haemorrhage, 1·83 mL (−12·01 to 15·66) for extra-axial haemorrhage, 2·09 mL (−9·38 to 13·56) for perilesional oedema, and 0·07 mL (−1·00 to 1·13) for intraventricular haemorrhage.InterpretationWe show the ability of a CNN to separately segment, quantify, and detect multiclass haemorrhagic lesions and perilesional oedema. These volumetric lesion estimates allow clinically relevant quantification of lesion burden and progression, with potential applications for personalised treatment strategies and clinical research in TBI.
dc.format
application/pdf
dc.language.iso
eng
dc.publisher
Elsevier
dc.rights
info:eu-repo/semantics/openAccess
dc.rights.uri
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
dc.subject
Deep Learning
dc.subject
Computer Tomography
dc.subject
Traumatic Brain Injury
dc.subject
Biomedical Image Segmentation
dc.subject.classification
Ciencias de la Computación
![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 Computación e Información
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.subject.classification
CIENCIAS NATURALES Y EXACTAS
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.title
Multiclass semantic segmentation and quantification of traumatic brain injury lesions on head CT using deep learning: an algorithm development and multicentre validation study
dc.type
info:eu-repo/semantics/article
dc.type
info:ar-repo/semantics/artículo
dc.type
info:eu-repo/semantics/publishedVersion
dc.date.updated
2020-07-01T19:53:49Z
dc.journal.volume
2
dc.journal.pagination
1-9
dc.journal.pais
Reino Unido
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.journal.ciudad
Londres
dc.description.fil
Fil: Monteiro, Miguel. Imperial College London; Reino Unido
dc.description.fil
Fil: Newcombe, Virginia F J. Imperial College London; Reino Unido
dc.description.fil
Fil: Mathieu, Francois. University of Cambridge; Reino Unido
dc.description.fil
Fil: Adatia, Krishma. University of Cambridge; Reino Unido
dc.description.fil
Fil: Kamnitsas, Konstantinos. Imperial College London; Reino Unido
dc.description.fil
Fil: Ferrante, Enzo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
dc.description.fil
Fil: Das, Tilak. University of Cambridge; Reino Unido
dc.description.fil
Fil: Whitehouse, Daniel. University of Cambridge; Reino Unido
dc.description.fil
Fil: Rueckert, Daniel. Imperial College London; Reino Unido
dc.description.fil
Fil: Menon, David K. University of Cambridge; Estados Unidos
dc.description.fil
Fil: Glocker, Ben. Imperial College London; Reino Unido
dc.journal.title
The Lancet Digital Health
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://linkinghub.elsevier.com/retrieve/pii/S2589750020300856
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1016/S2589-7500(20)30085-6
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://www.thelancet.com/journals/landig/article/PIIS2589-7500(20)30085-6/fulltext
Archivos asociados