Accurate and robust sparse-view angle CT image reconstruction using deep learning and prior image constrained compressed sensing (DL-PICCS).
Accurate and robust sparse-view angle CT image reconstruction using deep learning and prior image constrained compressed sensing (DL-PICCS).
复制标题
作者：
在动态CT采集中遇到的稀疏视图CT图像重建问题在技术上具有挑战性。近年来，人们提出了许多深度学习策略来从稀疏视角获取的图像中重建CT图像，并取得了良好的效果。然而，这些深度学习重建方法的两个基本问题仍有待解决：(1)对个体患者的重建准确性有限；(2)对患者统计队列的可泛化性有限。这项工作的目的是解决前面提到的当前深度学习方法中的挑战。为了解决这两个问题，提出了一种结合深度学习策略和先验图像约束压缩感知（PICCS）的方法。该方法首先利用传统的滤波反投影（FBP）方法对稀疏视图CT数据进行重构，然后利用训练好的深度神经网络进行处理，消除条纹伪影。然后将深度学习架构的输出用作PICCS中所需的先验图像来重建图像。如果PICCS重建的噪声水平不令人满意，则可以使用另一个轻型深度神经网络来降低噪声水平。大量的数值模拟数据和人体受试者数据已被用于定量和定性地评估所提出的DL-PICCS方法在重建精度和泛化方面的性能。大量的评估研究表明：(1)与深度学习方法和基于cs的方法相比，DL-PICCS对个体患者的定量重建精度有所提高；(2)在DL-PICCS重建图像中，深度学习方法中的假阳性病变样结构和假阴性缺失解剖结构可以有效消除；(3) DL-PICCS使深度学习方案能够放宽其工作条件，增强其泛化能力。DL-PICCS为实现个性化重建提供了很好的机会，同时提高了重建精度和增强了通用性。
Sparse-view CT image reconstruction problems encountered in dynamic CT acquisitions are technically challenging. Recently, many deep learning strategies have been proposed to reconstruct CT images from sparse-view angle acquisitions showing promising results. However, two fundamental problems with these deep learning reconstruction methods remain to be addressed: (1) limited reconstruction accuracy for individual patients and (2) limited generalizability for patient statistical cohorts. The purpose of this work is to address the previously mentioned challenges in current deep learning methods. A method that combines a deep learning strategy with prior image constrained compressed sensing (PICCS) was developed to address these two problems. In this method, the sparse-view CT data were reconstructed by the conventional filtered backprojection (FBP) method first, and then processed by the trained deep neural network to eliminate streaking artifacts. The outputs of the deep learning architecture were then used as the needed prior image in PICCS to reconstruct the image. If the noise level from the PICCS reconstruction is not satisfactory, another light duty deep neural network can then be used to reduce noise level. Both extensive numerical simulation data and human subject data have been used to quantitatively and qualitatively assess the performance of the proposed DL-PICCS method in terms of reconstruction accuracy and generalizability. Extensive evaluation studies have demonstrated that: (1) quantitative reconstruction accuracy of DL-PICCS for individual patient is improved when it is compared with the deep learning methods and CS-based methods; (2) the false-positive lesion-like structures and false negative missing anatomical structures in the deep learning approaches can be effectively eliminated in the DL-PICCS reconstructed images; and (3) DL-PICCS enables a deep learning scheme to relax its working conditions to enhance its generalizability. DL-PICCS offers a promising opportunity to achieve personalized reconstruction with improved reconstruction accuracy and enhanced generalizability.
登录
查看更多内容
基于神经网络的统计迭代CBCT重建
影响因子：
10.6
作者：
Chen B;Xiang K;Gong Z;Wang J;Tan S
通讯作者：
Tan S
影响因子：
3.3
作者：
Hammernik K;Klatzer T;Kobler E;Recht MP;Sodickson DK;Pock T;Knoll F
通讯作者：
Knoll F
DOI：
10.1109/tpami.2020.3012955
发表时间：
2023-04
影响因子：
23.6
作者：
Chun IY;Huang Z;Lim H;Fessler JA
通讯作者：
Fessler JA
影响因子：
2.8
作者：
Ge, Yongshuai;Su, Ting;Liang, Dong
通讯作者：
Liang, Dong
影响因子：
10.6
作者：
Chen GH;Theriault-Lauzier P;Tang J;Nett B;Leng S;Zambelli J;Qi Z;Bevins N;Raval A;Reeder S;Rowley H
通讯作者：
Rowley H