DeepSPIO: Super Paramagnetic Iron Oxide Particle Quantification using Deep Learning in Magnetic Resonance Imaging

Simple item page
dc.contributor.authordella Maggiora Valdés, Gabriel Eugenio
dc.contributor.authorMilovic Fabregat, Carlos Andrés
dc.contributor.authorQiu, Wenqi
dc.contributor.authorLiu, Shuang
dc.contributor.authorMilovic Fabregat, Carlos Andres
dc.contributor.authorSekino, Masaki
dc.contributor.authorTejos Nunez, Cristian Andres
dc.contributor.authorUribe Arancibia, Sergio A.
dc.contributor.authorIrarrazaval Barros, Pablo
dc.date.accessioned2022-05-18T14:39:47Z
dc.date.available2022-05-18T14:39:47Z
dc.date.issued2020
dc.description.abstractThe susceptibility of Super Paramagnetic Iron Oxide (SPIO) particles makes them a useful contrast agent for different purposes in MRI. These particles are typically quantified with relaxometry or by measuring the inhomogeneities they produced. These methods rely on the phase, which is unreliable for high concentrations. We present in this study a novel Deep Learning method to quantify the SPIO concentration distribution. We acquired the data with a new sequence called View Line in which the field map information is encoded in the geometry of the image. The novelty of our network is that it uses residual blocks as the bottleneck and multiple decoders to improve the gradient flow in the network. Each decoder predicts a different part of the wavelet decomposition of the concentration map. This decomposition improves the estimation of the concentration, and also it accelerates the convergence of the model. We tested our SPIO concentration reconstruction technique with simulated images and data from actual scans from phantoms. The simulations were done using images from the IXI dataset, and the phantoms consisted of plastic cylinders containing agar with SPIO particles at different concentrations. In both experiments, the model was able to quantify the distribution accurately.
dc.fuente.origenIEEE
dc.identifier.doi10.1109/TPAMI.2020.3012103
dc.identifier.issn1939-3539
dc.identifier.urihttps://doi.org/10.1109/TPAMI.2020.3012103
dc.identifier.urihttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9149791
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/64154
dc.information.autorucEscuela de ingeniería ; della Maggiora Valdés, Gabriel Eugenio ; S/I ; 203886
dc.information.autorucEscuela de ingeniería ; Castillo Passi, Carlos Andres ; S/I ; 204150
dc.information.autorucEscuela de ingeniería ; Milovic Fabregat, Carlos Andres ; S/I ; 120377
dc.information.autorucEscuela de ingeniería ; Tejos Nunez, Cristian Andres ; S/I ; 4027
dc.information.autorucEscuela de ingeniería ; Uribe Arancibia, Sergio Andres ; S/I ; 16572
dc.information.autorucEscuela de ingeniería ; Irarrazaval Barros, Pablo ; S/I ; 102769
dc.issue.numero1
dc.language.isoen
dc.nota.accesoContenido parcial
dc.pagina.final153
dc.pagina.inicio143
dc.revistaIEEE Transactions on Pattern Analysis and Machine Intelligence
dc.rightsacceso restringido
dc.subjectMagnetic resonance imaging
dc.subjectDecoding
dc.subjectDistortion
dc.subjectMachine learning
dc.subjectMagnetic susceptibility
dc.subjectConvolution
dc.subjectImage reconstruction
dc.titleDeepSPIO: Super Paramagnetic Iron Oxide Particle Quantification using Deep Learning in Magnetic Resonance Imaginges_ES
dc.typeartículo
dc.volumen44
sipa.codpersvinculados203886
sipa.codpersvinculados204150
sipa.codpersvinculados120377
sipa.codpersvinculados4027
sipa.codpersvinculados16572
sipa.codpersvinculados102769
Files
Collections
Artículos de revistas