Loading...

Dose Reduction Via Development of a Novel Image Reconstruction Method for Few-View Computed Tomography

Khodajou Chokami, Hamid Reza | 2022

75 Viewed
  1. Type of Document: Ph.D. Dissertation
  2. Language: Farsi
  3. Document No: 55743 (46)
  4. University: Sharif University of Technology
  5. Department: Energy Engineering
  6. Advisor(s): Hosseini, Abolfazl; Ay, Mohammad Reza
  7. Abstract:
  8. Sparse-view computed tomography (CT) is recently proposed as a promising method to speed up data acquisition and alleviate the issue of CT high-dose delivery to patients. However, traditional reconstruction algorithms are time-consuming and suffer from image degradation when faced with sparse-view data. To address this problem, we propose two new frameworks based on deep learning (DL) that can quickly produce high-quality CT images from sparsely sampled projections and is able for clinical use. Our first DL-based proposed model is based on the convolution, and residual neural networks in a parallel manner, named the parallel residual neural network (PARS-Net). Besides, our proposed PARS-Net model benefits from a loss based on the geodesic distance to reflect image structures effectively. Our second approach is named the multi-receptive field densely connected CNN (MRDC-CNN). MRDC-CNN benefits from an encoder–decoder structure by proposing dense skip connections to recover the missing information, multi-receptive field modules to enlarge the receptive field, and having no batch normalization layers to boost the performance. The MRDC-CNN with a hybrid loss function format introduces several auxiliary losses combined with the main loss to accelerate the convergence rate, alleviate the gradient vanishing problem during network training, and maximize its performance. Experiments have been performed on the combination of two large-scale CT datasets consisting of CT images of whole-body patients for different sparse projection views, including 120, 60, and 30 views. Our experimental results show that our PARS-Net and MRDC-CNN, respectively, are 4–6 times and 4–5 times faster than the state-of-the-art DL-based models, with fewer memory requirements, better performance in other objective quality evaluations, and improved visual quality. The results indicated our proposed methods' superiority over the latest algorithms. In conclusion, the proposed methods could lead to high-quality CT imaging with quicker imaging speed and lower radiation dose
  9. Keywords:
  10. Deep Learning ; Image Reconstruction ; Computed Tomography (CT) ; Encoder-Decoder ; Convolutional Neural Network ; Sparse Sampeling ; Image Reconstruction

 Digital Object List

 Bookmark

No TOC