DeepSPIO: Super paramagnetic iron oxide particle quantification using deep learning in magnetic resonance imaging

DeepSPIO: Super paramagnetic iron oxide particle quantification using deep learning in magnetic resonance imaging

Magnetic resonance imaging

Decoding

Distortion

Machine learning

Magnetic susceptibility

Convolution

Image reconstruction

620

Ingeniería

Tesis (Master of Science in Engineering)--Pontificia Universidad Católica de Chile, 2019

The 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.

Della Maggiora Valdés, Gabriel Eugenio

2022-10-27T18:25:46Z

2022-10-27T18:25:46Z

2019

Irarrázaval Mena, Pablo

Pontificia Universidad Católica de Chile. Escuela de Ingeniería

acceso abierto

xii, 33 páginas

application/pdf

en

tesis de maestría

10.7764/tesisUC/ING/65152

https://doi.org/10.7764/tesisUC/ING/65152

https://repositorio.uc.cl/handle/11534/65152