Dual-domain attention-guided convolutional neural network for low-dose cone-beam computed tomography reconstruction

作者：

Highlights：

• A novel dual-domain deep learning framework for low-dose CT reconstruction.

• A 3D spatial attention module for well utilizing the intra- and inter-images information.

• A novel joint loss function for circumventing the structures loss and over-smoothness.

• Consistently good performance was obtained on both simulated and real datasets.

摘要

•A novel dual-domain deep learning framework for low-dose CT reconstruction.•A 3D spatial attention module for well utilizing the intra- and inter-images information.•A novel joint loss function for circumventing the structures loss and over-smoothness.•Consistently good performance was obtained on both simulated and real datasets.

论文关键词：Cone-beam computed tomography,Low-dose,Deep learning,Convolutional neural network,Image reconstruction

论文评审过程：Received 24 January 2022, Revised 15 June 2022, Accepted 16 June 2022, Available online 21 June 2022, Version of Record 4 July 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.109295