3D U-NetR: Low Dose Computed Tomography Reconstruction via Deep Learning and 3 Dimensional Convolutions
arXiv:2105.14130
Abstract
In this paper, we introduced a novel deep learning-based reconstruction technique for low-dose CT imaging using 3 dimensional convolutions to include the sagittal information unlike the existing 2 dimensional networks which exploits correlation only in transverse plane. In the proposed reconstruction technique, sparse and noisy sinograms are back-projected to the image domain with FBP operation, then the denoising process is applied with a U-Net like 3-dimensional network called 3D U-NetR. The proposed network is trained with synthetic and real chest CT images, and 2D U-Net is also trained with the same dataset to show the importance of the third dimension in terms of recovering the fine details. The proposed network shows better quantitative performance on SSIM and PSNR, especially in the real chest CT data. More importantly, 3D U-NetR captures medically critical visual details that cannot be visualized by a 2D network on the reconstruction of real CT images with 1/10 of the normal dose.
arXiv comment18 pages, 5 figures
References in corpus (6)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)
- Image reconstruction by domain transform manifold learning
- Medical image denoising using convolutional denoising autoencoders
- An Unsupervised Reconstruction Method For Low-Dose CT Using Deep Generative Regularization Prior