Denoising PET images using singular value thresholding and stein’s unbiased risk estimate
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2013: 16th International Conference, Nagoya, Japan, September 22–26, 2013, Proceedings, Part III, Lecture Notes in Computer Science, volume 8151, pages 115–122
Abstract
Image denoising is an important pre-processing step for accurately quantifying functional morphology and measuring activities of the tissues using PET images. Unlike structural imaging modalities, PET images have two difficulties: (1) the Gaussian noise model does not necessarily fit into PET imaging because the exact nature of noise propagation in PET imaging is not well known, and (2) PET images are low resolution; therefore, it is challenging to denoise them while preserving structural information. To address these two difficulties, we introduce a novel methodology for denoising PET images. The proposed method uses the singular value thresholding concept and Stein's unbiased risk estimate to optimize a soft thresholding rule. Results, obtained from 40 MRI-PET images, demonstrate that the proposed algorithm is able to denoise PET images successfully, while still maintaining the quantitative information.
Abstract sourceThis MICCAI 2013 paper presents a PET image-denoising method that combines singular value soft thresholding with Stein’s unbiased risk estimate to select a threshold. The authors evaluate it on 40 MRI-PET image sets.
Summary
The paper addresses noise reduction in positron emission tomography (PET) images while seeking to preserve structural detail and quantitative information. The method applies a variance-stabilizing transform, singular value soft thresholding, and Stein’s unbiased risk estimate to choose the threshold; the denoised image is then transformed back to the standardized uptake value domain.
The authors evaluated the method using 40 MRI-PET image sets and compared image measures with several filtering approaches. They report that the method reduced noise while maintaining quantitative information, including SUVmax and SUVmean. These findings are from the study’s reported evaluation; they do not establish prospective clinical validation or clinical readiness.
Cite this work
Ulas Bagci; Daniel J. Mollura (2013). Denoising PET images using singular value thresholding and stein’s unbiased risk estimate. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2013: 16th International Conference, Nagoya, Japan, September 22–26, 2013, Proceedings, Part III, Lecture Notes in Computer Science, volume 8151, pages 115–122 https://doi.org/10.1007/978-3-642-40760-4_15
BibTeX