Learning-Based Material Decomposition in Dual Energy CT Using an Unrolled Estimator
Learning-Based Material Decomposition in Dual Energy CT Using an Unrolled Estimator
复制标题
DOI：
10.1109/isbi53787.2023.10230700
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Megan Lantz;Greg Ongie
中科院分区：
文献类型：
--
作者：
Megan Lantz;Greg Ongie
在双能量CT中重建多个特定材料的图像是一个具有挑战性的非线性逆问题。传统上，重建过程包括两个步骤：材料分解和层析重建。基于模型的迭代重建方法将联合收割机材料分解和层析重建结合到统一的“一步”框架中，提供了改进的估计，但需要更长的重建时间。为了解决这个问题，我们提出了一种监督机器学习技术来加速一步迭代双能量CT重建。具体来说，我们训练了一个嵌入在基于模型的迭代算法的“展开”中的深度神经网络。我们证明了这种方法上的问题，识别三种材料（脂肪组织，纤维腺体组织，钙化）从模拟乳房双能CT数据。从经验上讲，我们发现，展开方法在几次迭代中给出了准确的材料图估计，并且优于基线图像域学习方法。
Reconstructing multiple material-specific images in dual-energy CT is a challenging non-linear inverse problem. Traditionally, the reconstruction process consists of two steps: material decomposition and tomographic reconstruction. Model-based iterative reconstruction methods that combine material decomposition and tomographic reconstruction into a unified "one-step" framework provide improved estimates, but require longer reconstruction times. To address this, we propose a supervised machine learning technique to accelerate one-step iterative dual-energy CT reconstruction. Specifically, we train a deep neural network embedded in an "unrolling" of a model-based iterative algorithm. We demonstrate this approach on the problem of identifying three materials (adipose tissue, fibroglandular tissue, and calcifications) from simulated breast dual-energy CT data. Empirically, we find that the unrolling approach gives accurate material map estimates in few iterations, and outperforms a baseline image-domain learning approach.