A novel simulation‐driven reconstruction approach for x‐ray computed tomography

Abstract

Radiation dose reduction is critical to the success of x-ray computed tomography (CT). Many advanced reconstruction techniques have been developed over the years to combat noise resulting from the low-dose CT scans. These algorithms rely on accurate local estimation of the image noise to determine reconstruction parameters or to select inferencing models. Because of the difficulties in the noise estimation for heterogeneous objects, the performance of many algorithms is inconsistent and suboptimal. Here, we propose a novel approach to overcome such shortcoming. Method: By injecting appropriate amount of noise in the CT raw data, a computer simulation approach is capable of accurately estimating the local statistics of the raw data and the local noise in the reconstructed images. This information is then used to guide the noise-reduction process during the reconstruction. As an initial implementation, a scaling map is generated based on the noise predicted from the simulation and the noise estimated from existing reconstruction algorithms. Images generated with existing algorithms are subsequently modified based on the scaling map. In this study, both iterative reconstruction (IR) and deep learning image reconstruction (DLIR) algorithms are evaluated. Results: Phantom experiments were conducted to evaluate the performance of the simulation-based noise estimation in terms of the standard deviation and noise power spectrum. Quantitative results have demonstrated that the noise measured from the original image matches well with the noise estimated from the simulation. Clinical datasets were utilized to further confirm the accuracy of the proposed approach under more challenging conditions. To validate the performance of the proposed reconstruction approach, clinical scans were used. Performance comparison was carried out qualitatively and quantitatively. Two existing advanced reconstruction techniques, IR and DLIR, were evaluated against the proposed approach. Results have shown that the proposed approach outperforms existing IR and DLIR algorithms in terms of noise suppression and, equally importantly, noise uniformity across the entire imaging volume. Visual assessment of the images also reveals that the proposed approach does not endure noise texture issues faced by some of the existing reconstruction algorithms today. Conclusion:Phantom and clinical results have demonstrated superior performance of the proposed approach with regard to noise reduction as well as noise homogeneity. Visual inspection of the noise texture further confirms the clinical utility of the proposed approach. Future enhancements on the current implementation are explored regarding image quality and computational efficiency.Because of the limited scope of this paper,detailed investigation on these enhancement features will be covered in a separate report.

Synthetization of high‐dose images using low‐dose CT scans

“…Based on extensive experiments, we found that the non‐local means (NLM) filter, Γ h , performs the best in removing correlated noise in CT images, where h specifies the “degree of smoothing.” 30 The parameter h , which controls the sizes of the similarity‐window and the search‐window, is driven by the standard deviation, σ, in the image. Our previous study has shown that the noise in d ( x , y ) can be accurately estimated by a noise‐insertion process when the scan data is available 26 . It has been demonstrated that the noise estimated with such approach is accurate not only on a global scale, but also in local regions.…”

“…Our previous study has shown that the noise in d(x, y) can be accurately estimated by a noise-insertion process when the scan data is available. 26 It has been demonstrated that the noise estimated with such approach is accurate not only on a global scale, but also in local regions. The accuracy of the noise estimation is not influenced or biased by the presence of complex anatomical structures.…”

“…Deep learning (DL) has been explored in recent years for CT noise‐reduction as part of image reconstruction or post‐processing 19–28 . To further enhance the noise‐reduction capability, a dynamically selected image volume is utilized to produce a single image 29 .…”

“…18 Deep learning (DL) has been explored in recent years for CT noise-reduction as part of image reconstruction or post-processing. [19][20][21][22][23][24][25][26][27][28] To further enhance the noise-reduction capability, a dynamically selected image volume is utilized to produce a single image. 29 When proper training datasets are used, DL has shown significant noise-reduction capability while preserving the FBP-like peak-frequency in NPS.…”

Generation of training dataset for deep-learning noise reduction

“…14 Deep learning (DL) has been explored in recent years for CT noise-reduction as part of the image reconstruction or the post-processing. [14][15][16][17][18][19][20][21] When proper training datasets are used, DL has shown significant noise-reduction capability while preserving the FBP-like peak-frequency in NPS. In DL, the production of the ground-truth images (GTI) is critical, since DL relies heavily on large training datasets to achieve high accuracy.…”