Denoising of dynamic PET images using a multi-scale transform and non-local means filter

Jomaa, Hajer; Mabrouk, Rostom; Khlifa, Nawrès; Morain-Nicolier, Frédéric

doi:10.1016/j.bspc.2017.11.002

Cited by 24 publications

(21 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other noise reduction approaches consist in the image post-filtering, from the simple Gaussian mean to the more complex non-local means [ 4 ], possibly including anatomical priors [ 5 ]. Non-stationary approaches, such as multi-scale transform (curvelet or wavelet) [ 6 , 7 ] have proven to be also of great interest to provide a significant reduction of noise while preserving contrast and important structures [ 8 , 9 ].…”

Section: Introductionmentioning

confidence: 99%

Clinical and phantom validation of a deep learning based denoising algorithm for F-18-FDG PET images from lower detection counting in comparison with the standard acquisition

et al. 2022

View full text Add to dashboard Cite

Background PET/CT image quality is directly influenced by the F-18-FDG injected activity. The higher the injected activity, the less noise in the reconstructed images but the more radioactive staff exposition. A new FDA cleared software has been introduced to obtain clinical PET images, acquired at 25% of the count statistics considering US practices. Our aim is to determine the limits of a deep learning based denoising algorithm (SubtlePET) applied to statistically reduced PET raw data from 3 different last generation PET scanners in comparison to the regular acquisition in phantom and patients, considering the European guidelines for radiotracer injection activities. Images of low and high contrasted (SBR = 2 and 5) spheres of the IEC phantom and high contrast (SBR = 5) of micro-spheres of Jaszczak phantom were acquired on 3 different PET devices. 110 patients with different pathologies were included. The data was acquired in list-mode and retrospectively reconstructed with the regular acquisition count statistic (PET100), 50% reduction in counts (PET50) and 66% reduction in counts (PET33). These count reduced images were post-processed with SubtlePET to obtain PET50 + SP and PET33 + SP images. Patient image quality was scored by 2 senior nuclear physicians. Peak-signal-to-Noise and Structural similarity metrics were computed to compare the low count images to regular acquisition (PET100). Results SubtlePET reliably denoised the images and maintained the SUVmax values in PET50 + SP. SubtlePET enhanced images (PET33 + SP) had slightly increased noise compared to PET100 and could lead to a potential loss of information in terms of lesion detectability. Regarding the patient datasets, the PET100 and PET50 + SP were qualitatively comparable. The SubtlePET algorithm was able to correctly recover the SUVmax values of the lesions and maintain a noise level equivalent to full-time images. Conclusion Based on our results, SubtlePET is adapted in clinical practice for half-time or half-dose acquisitions based on European recommended injected dose of 3 MBq/kg without diagnostic confidence loss.

show abstract

Section: Introductionmentioning

confidence: 99%

Clinical and phantom validation of a deep learning based denoising algorithm for F-18-FDG PET images from lower detection counting in comparison with the standard acquisition

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Common image filtering techniques, such as nonlocal means and block matching, are well established in the field. [12][13][14] Despite achieving higher visual quality, these methods tend to have reliance on a large number of parameters that are yet to be standardized.…”

Section: Introductionmentioning

confidence: 99%

“…Post‐reconstruction methods that use image filtering or sparse methods to predict standard‐dose PET from low‐dose PET 11 have also succeeded in denoising PET images. Common image filtering techniques, such as nonlocal means and block matching, are well established in the field 12–14 . Despite achieving higher visual quality, these methods tend to have reliance on a large number of parameters that are yet to be standardized.…”

Section: Introductionmentioning

confidence: 99%

Full‐count PET recovery from low‐count image using a dilated convolutional neural network

et al. 2020

View full text Add to dashboard Cite

Purpose: Positron emission tomography (PET) is an essential technique in many clinical applications that allows for quantitative imaging at the molecular level. This study aims to develop a denoising method using a novel dilated convolutional neural network (CNN) to recover full-count images from low-count images. Methods: We adopted similar hierarchical structures as the conventional U-Net and incorporated dilated kernels in each convolution to allow the network to observe larger, more robust features within the image without the requirement of downsampling and upsampling internal representations. Our dNet was trained alongside a U-Net for comparison. Both models were evaluated using a leaveone-out cross-validation procedure on a dataset of 35 subjects (~3500 slabs), which were obtained from an ongoing 18 F-Fluorodeoxyglucose (FDG) study. Low-count PET data (10% count) were generated by randomly selecting one-tenth of all events in the associated listmode file. Analysis was done on the static image from the last 10 minutes of emission data. Both low-count PET and full-count PET were reconstructed using ordered subset expectation maximization (OSEM). Objective image quality metrics, including mean absolute percent error (MAPE), peak signal-to-noise ratio (PSNR), and structural similarity index metric (SSIM), were used to analyze the deep learning methods. Both deep learning methods were further compared to a traditional Gaussian filtering method. Further, region of interest (ROI) quantitative analysis was also used to compare U-Net and dNet architectures. Results: Both the U-Net and our proposed network were successfully trained to synthesize fullcount PET images from the generated low-count PET images. Compared to low-count PET and Gaussian filtering, both deep learning methods improved MAPE, PSNR, and SSIM. Our dNet also systematically outperformed U-Net on all three metrics (MAPE: 4.99 AE 0.68 vs 5.31 AE 0.76, P < 0.01; PSNR: 31.55 AE 1.31 dB vs 31.05 AE 1.39, P < 0.01; SSIM: 0.9513 AE 0.0154 vs 0.9447 AE 0.0178, P < 0.01). ROI quantification showed greater quantitative improvements using dNet over U-Net. Conclusion: This study proposed a novel approach of using dilated convolutions for recovering fullcount PET images from low-count PET images.

show abstract

“…Thus, denoising is a must before any subsequent manipulation. A mean filter [1–3] as a low‐pass filter is unable to preserve edges and details, so a median filter is usually used to remove impulse noises.…”

Section: Introductionmentioning

confidence: 99%

Iterative grouping median filter for removal of fixed value impulse noise

Chen

Zhan

Cao

et al. 2019

IET Image Processing

View full text Add to dashboard Cite

Denoising of dynamic PET images using a multi-scale transform and non-local means filter

Cited by 24 publications

References 35 publications

Clinical and phantom validation of a deep learning based denoising algorithm for F-18-FDG PET images from lower detection counting in comparison with the standard acquisition

Clinical and phantom validation of a deep learning based denoising algorithm for F-18-FDG PET images from lower detection counting in comparison with the standard acquisition

Full‐count PET recovery from low‐count image using a dilated convolutional neural network

Iterative grouping median filter for removal of fixed value impulse noise

Contact Info

Product

Resources

About