Self-supervised CT super-resolution with hybrid model. (November 2021)

• Record Type: Journal Article
• Authors: Zhang, Zhicheng; Yu, Shaode; Qin, Wenjian; Liang, Xiaokun; Xie, Yaoqin; Cao, Guohua
• Is Part Of: Computers in biology and medicine. Volume 138(2021)
• Publication Date: 2021-11
• Subjects: Computed tomography -- Super resolution -- Self-supervised -- Hybrid model; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.104775
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Software-based methods can improve CT spatial resolution without changing the hardware of the scanner or increasing the radiation dose to the object. In this work, we aim to develop a deep learning (DL) based CT super-resolution (SR) method that can reconstruct low-resolution (LR) sinograms into high-resolution (HR) CT images. We mathematically analyzed imaging processes in the CT SR imaging problem and synergistically integrated the SR model in the sinogram domain and the deblur model in the image domain into a hybrid model (SADIR). SADIR incorporates the CT domain knowledge and is unrolled into a DL network (SADIR-Net). The SADIR-Net is a self-supervised network, which can be trained and tested with a single sinogram. SADIR-Net was evaluated through SR CT imaging of a Catphan 700 physical phantom and a real porcine phantom, and its performance was compared to the other state-of-the-art (SotA) DL-based CT SR methods. On both phantoms, SADIR-Net obtains the highest information fidelity criterion (IFC), structure similarity index (SSIM), and lowest root-mean-square-error (RMSE). As to the modulation transfer function (MTF), SADIR-Net also obtains the best result and improves the MTF50% by 69.2% and MTF10% by 69.5% compared with FBP. Alternatively, the spatial resolutions at MTF50% and MTF10% from SADIR-Net can reach 91.3% and 89.3% of the counterparts reconstructed from the HR sinogram with FBP. The results show that SADIR-Net can provide performance comparable to the other SotA methods for CT SR reconstruction, especially in the case of extremely limited training data or even no data at all. Thus, the SADIR method could find use in improving CT resolution without changing the hardware of the scanner or increasing the radiation dose to the object. Graphical abstract: Image 1 Highlights: SADIR-Net is a hybrid model for CT SR that combines the DL techniques with CT domain knowledge. SADIR-Net is a lightweight neural network with fewer network parameters. SADIR-Net is a self-supervised method for CT SR imaging without any extra training dataset.