Cas-PRED: A Limited-Angle Cone Beam CT Reconstruction Research Based on Prior Information
- 30 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-17
Abstract
Due to limitations in radiation dose or scanning conditions, there are instances where CT data can only be collected within a restricted scanning angle. However, the use of limited-angle projection data often results in reconstructed images that exhibit significant noise and artifacts, which can significantly impact diagnostic accuracy. Conventional iterative reconstruction algorithms, such as the total variation algorithm, consume considerable time simulating the cone beam forward and backward projection processes. Furthermore, these algorithms often struggle to address the challenges of limited-angle reconstruction due to their inherent limitations. To tackle these challenges and achieve superior reconstruction outcomes, we introduce a novel approach known as the Cascaded Prior-Based Residual Encoder-Decoder Network (Cas-PRED). This method employs a multi-level cascaded network as its core architecture, leveraging full-angle CT reconstruction results as prior information to guide the deep learning network’s training process. Our approach consistently delivers superior results compared to existing reconstruction methods, with impressive performance metrics, including a peak signal-to-noise ratio (PSNR) of 33.69±0.90 dB, a structural similarity index (SSIM) of 0.9557±0.0029, and a root mean squared error (RMSE) of 22.73±1.56 for the result of [0, 150°] reconstruction, highlighting its effectiveness in enhancing image quality and accuracy.Keywords
Funding Information
- State Key Project of Research and Development Plan (2022YFC2408500, 2022YFC2401600)
- National Key Research and Development Program of China (2022YFE0116700)
- National Natural Science Foundation of China (T2225025)
- Key Research and development Programs in Jiangsu Province of China (BE2021703, BE2022768)
- Jiangsu Province Science Foundation for Youths (BK20220825)
- Big Data Computing Center of Southeast University
This publication has 45 references indexed in Scilit:
- A model-based deep network for limited-angle computed tomography image reconstructionDisplays, 2022
- Directional-TV algorithm for image reconstruction from limited-angular-range dataMedical Image Analysis, 2021
- Detection Method of Pile Foundation on Subway Lines Based on Cross-Hole Resistivity Computed TomographyJournal of Performance of Constructed Facilities, 2020
- Medical image segmentation using deep learning with feature enhancementIET Image Processing, 2020
- Image reconstruction model for limited-angle CT based on prior image induced relative total variationApplied Mathematical Modelling, 2019
- Deep Learning Techniques for Medical Image Segmentation: Achievements and ChallengesJournal of Digital Imaging, 2019
- A deep learning framework for unsupervised affine and deformable image registrationMedical Image Analysis, 2019
- A survey on deep learning in medical image analysisMedical Image Analysis, 2017
- ALARA (as low as reasonably achievable) CT 2011—executive summaryPediatric Radiology, 2011
- Nonlinear total variation based noise removal algorithmsPhysica D: Nonlinear Phenomena, 1992