Mostrar el registro sencillo del ítem

dc.contributor.author
Thomsen, Felix Sebastian Leo  
dc.contributor.author
Delrieux, Claudio Augusto  
dc.contributor.author
Pisula, Juan I.  
dc.contributor.author
Fuertes García, José M.  
dc.contributor.author
Lucena, Manuel  
dc.contributor.author
de Luis García, Rodrigo  
dc.contributor.author
Borggrefe, Jan  
dc.date.available
2021-02-19T13:53:00Z  
dc.date.issued
2020-12  
dc.identifier.citation
Thomsen, Felix Sebastian Leo; Delrieux, Claudio Augusto; Pisula, Juan I.; Fuertes García, José M.; Lucena, Manuel; et al.; Noise reduction using novel loss functions to compute tissue mineral density and trabecular bone volume fraction on low resolution QCT; Pergamon-Elsevier Science Ltd; Computerized Medical Imaging and Graphics; 86; 101816; 12-2020; 1-9  
dc.identifier.issn
0895-6111  
dc.identifier.uri
http://hdl.handle.net/11336/126070  
dc.description.abstract
Micro-structural parameters of the thoracic or lumbar spine generally carry insufficient accuracy and precision for clinical in vivo studies when assessed on quantitative computed tomography (QCT). We propose a 3D convolutional neural network with specific loss functions for QCT noise reduction to compute micro-structural parameters such as tissue mineral density (TMD) and bone volume ratio (BV/TV) with significantly higher accuracy than using no or standard noise reduction filters. The vertebra-phantom study contained high resolution peripheral and clinical CT scans with simulated in vivo CT noise and nine repetitions of three different tube currents (100, 250 and 360 mAs). Five-fold cross validation was performed on 20466 purely spongy pairs of noisy and ground-truth patches. Comparison of training and test errors revealed high robustness against over-fitting. While not showing effects for the assessment of BMD and voxel-wise densities, the filter improved thoroughly the computation of TMD and BV/TV with respect to the unfiltered data. Root-mean-square and accuracy errors of low resolution TMD and BV/TV decreased to less than 17% of the initial values. Furthermore filtered low resolution scans revealed still more TMD- and BV/TV-relevant information than high resolution CT scans, either unfiltered or filtered with two state-of-the-art standard denoising methods. The proposed architecture is threshold and rotational invariant, applicable on a wide range of image resolutions at once, and likely serves for an accurate computation of further micro-structural parameters. Furthermore, it is less prone for over-fitting than neural networks that compute structural parameters directly. In conclusion, the method is potentially important for the diagnosis of osteoporosis and other bone diseases since it allows to assess relevant 3D micro-structural information from standard low exposure CT protocols such as 100 mAs and 120 kVp.  
dc.format
application/pdf  
dc.language.iso
eng  
dc.publisher
Pergamon-Elsevier Science Ltd  
dc.rights
info:eu-repo/semantics/restrictedAccess  
dc.rights.uri
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/  
dc.subject
CONVOLUTIONAL NEURAL NETWORK  
dc.subject
IN VIVO  
dc.subject
LOCAL MICRO-STRUCTURE  
dc.subject
PHANTOM STUDY  
dc.subject
REGRESSION  
dc.subject.classification
Ciencias de la Información y Bioinformática  
dc.subject.classification
Ciencias de la Computación e Información  
dc.subject.classification
CIENCIAS NATURALES Y EXACTAS  
dc.title
Noise reduction using novel loss functions to compute tissue mineral density and trabecular bone volume fraction on low resolution QCT  
dc.type
info:eu-repo/semantics/article  
dc.type
info:ar-repo/semantics/artículo  
dc.type
info:eu-repo/semantics/publishedVersion  
dc.date.updated
2021-02-10T16:58:05Z  
dc.journal.volume
86  
dc.journal.number
101816  
dc.journal.pagination
1-9  
dc.journal.pais
Estados Unidos  
dc.description.fil
Fil: Thomsen, Felix Sebastian Leo. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina  
dc.description.fil
Fil: Delrieux, Claudio Augusto. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina  
dc.description.fil
Fil: Pisula, Juan I.. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina  
dc.description.fil
Fil: Fuertes García, José M.. Universidad de Jaén; España  
dc.description.fil
Fil: Lucena, Manuel. Universidad de Jaén; España  
dc.description.fil
Fil: de Luis García, Rodrigo. Universidad de Valladolid; España  
dc.description.fil
Fil: Borggrefe, Jan. Universitätsinstitut für Radiologie, Neuroradiologie und Nuklearmedizin, Hans-Nolte-Str; Alemania  
dc.journal.title
Computerized Medical Imaging and Graphics  
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://linkinghub.elsevier.com/retrieve/pii/S0895611120301117  
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1016/j.compmedimag.2020.101816