论文阅读 [TPAMI-2022] DeepSPIO: Super Paramagnetic Iron Oxide Particle Quantification Using Deep Learnin

论文阅读 [TPAMI-2022] DeepSPIO: Super Paramagnetic Iron Oxide Particle Quantification Using Deep Learning in Magnetic Resonance Imaging

论文搜索(studyai.com)

搜索论文: DeepSPIO: Super Paramagnetic Iron Oxide Particle Quantification Using Deep Learning in Magnetic Resonance Imaging

搜索论文: http://www.studyai.com/search/whole-site/?q=DeepSPIO:+Super+Paramagnetic+Iron+Oxide+Particle+Quantification+Using+Deep+Learning+in+Magnetic+Resonance+Imaging

关键字(Keywords)

Magnetic resonance imaging; Decoding; Distortion; Machine learning; Magnetic susceptibility; Convolution; Image reconstruction; Machine learning; deep learning; neural networks; MRI; quantification; susceptibility; QSM; SPIO

机器视觉

图像重建

摘要(Abstract)

The susceptibility of super paramagnetic iron oxide (SPIO) particles makes them a useful contrast agent for different purposes in MRI.

超顺磁性氧化铁（SPIO）粒子的磁化率使其成为MRI中不同用途的有用对比剂。.

These particles are typically quantified with relaxometry or by measuring the inhomogeneities they produced.

这些颗粒通常通过松弛计或测量它们产生的不均匀性来量化。.

These methods rely on the phase, which is unreliable for high concentrations.

这些方法依赖于相，这对于高浓度是不可靠的。.

We present in this study a novel Deep Learning method to quantify the SPIO concentration distribution.

在这项研究中，我们提出了一种新的深度学习方法来量化SPIO浓度分布。.

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.

我们用一种称为“视图线”的新序列获取数据，在该序列中，场地图信息被编码到图像的几何结构中。.

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.

我们网络的新颖之处在于，它使用剩余块作为瓶颈，并使用多个解码器来改善网络中的梯度流。.

Each decoder predicts a different part of the wavelet decomposition of the concentration map.

每个解码器预测浓度图小波分解的不同部分。.

This decomposition improves the estimation of the concentration, and also it accelerates the convergence of the model.

这种分解改进了浓度的估计，也加快了模型的收敛速度。.

We tested our SPIO concentration reconstruction technique with simulated images and data from actual scans from phantoms.

我们用模拟图像和来自模型的实际扫描数据测试了SPIO浓度重建技术。.

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.

模拟是使用来自IXI数据集的图像进行的，模型由含有不同浓度SPIO颗粒的琼脂的塑料圆筒组成。.

In both experiments, the model was able to quantify the distribution accurately…

在这两个实验中，该模型能够准确地量化分布。。.

作者(Authors)

[‘Gabriel della Maggiora’, ‘Carlos Castillo-Passi’, ‘Wenqi Qiu’, ‘Shuang Liu’, ‘Carlos Milovic’, ‘Masaki Sekino’, ‘Cristian Tejos’, ‘Sergio Uribe’, ‘Pablo Irarrazaval’]