Advanced Image Processing Using Feature Images Extracted from Different Iterations

Chuanyong Bai, Andriy Andreyev, Bin Zhang, Yang-Ming Zhu, Xiyun Song, Jinghan Ye, Zhiqiang Hu


Published in:Fully3D 2017 Proceedings


PET, iterative image reconstruction, evolution, feature image, TOF, filtering
In iterative image reconstruction, different structures may reconstruct or evolve at different rates with iterations. From the difference between the images at different iterations, we extract feature images based on the evolution characteristics of different structures. We then use the feature images for advanced image processing. A TOF list-mode OSEM algorithm was used for iterative image reconstruction. A methodology was established to calculate feature images which distinguish regions of fast evolution (presumably associated with large and uniform structures) and slow evolution (associated with small structures such as lesions and cold regions). The feature images were then used to guide the in-reconstruction noise-suppression approaches (such as regularized reconstruction) and post-reconstruction noise-suppression approaches. Phantom and patient studies were used to demonstrate the proposed technique and its advantages. Results showed that with the feature images even very simple image domain techniques could achieve superior performance for the intended applications.
Chuanyong Bai
Philips Medicals
Andriy Andreyev
Philips Medicals
Bin Zhang
Philips Medicals
Yang-Ming Zhu
Philips Medicals
Xiyun Song
Philips Medicals
Jinghan Ye
Philips Medicals
Zhiqiang Hu
Philips Medicals
  1. Tomasi C and Manduchi R, “Bilateral filtering for gray and color images,” Proceedings of the 1998 IEEE International Conference on Computer Vision,Bombay, India, 1998.
  2. Zeng GL and Allred RJ, “Partitioned image filtering for reduction of the Gibbs phenomenon,” J. Nucl. Med. Technol., June 2009, vol. 37, no. 2 96-100.
  3. He K, Sun J, and Tang X, “Guided image filtering,” IEEE Trans. Patt. Anal. Mach. Intell., June 2013, vol.35, issue 6, 1397-1409.
  4. Buades A, Coll B, and Morel J, “Non-local means denoising,” Image Processing On Line, 2011.
  5. Bai C, Andreyev A, Zhang B, et al, “Feature-based image processing using feature images extracted from different iterations,” (in process) US patent application, 2016.
  6. Demirkaya O, “Post-reconstruction filtering of positron emission tomography whole-body emission images and attenuation maps using nonlinear diffusion filtering,” 2004, Acad. Radiol., vol. 11, 1105–1114.
  7. Andreyev A, Bai C, Zhang B, and et al, “Evolutionscaled quadratic prior for iterative reconstruction in PET,” (abstract, unpublished), submitted to Annual Meeting of SNMMI, 2017.