Denoising of PET images by context modelling using local neighbourhood correlation

Huerga, C.; Castro, Pablo; Corredoira, E.; Coronado, Mónica; Delgado, V.; Guibelalde, E.

doi:10.1088/1361-6560/62/2/633

Cited by 14 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An example is found in the new filter based on wavelets proposed in (Huerga et al 2017). The improvement in the usual metrics has already been performed.…”

Section: Post-reconstruction Filter Comparing: Phantommentioning

confidence: 99%

Easy blur estimation in PET images including motion corrupted edges

Huerga¹,

Castro²,

Alejo³

et al. 2019

Biomed. Phys. Eng. Express

Self Cite

View full text Add to dashboard Cite

The PET image is often described as blurred, however, it is our knowledge that very few studies are focused on the evaluation of blurring in clinical images. This paper describes an easy and practical method for global blurring estimation of PET images based on the analysis of the objects edge. This blur index is associated with the full width at half maximum ( fwhm) of edges response to first-order directional Gaussian derivative operator. Two types of edges are considered: in addition to the usually considered edges corrupted by Gaussian filtering, an estimate of corrupted edges by motion is also included. The procedure verification is carried out in different radioactive environments with different signal-to-background ratio (S/B) and applying post-processed Gaussian filters with kernel sizes from 3 mm to 9 mm and through a mobile platform that induces a simple harmonic motion of different amplitudes from 3 mm to 15 mm. The results show that the proposed procedure is able to distinguish the induced blurring, either due to filtering or motion applied. It is robust to parameters selection and it could be applied to clinical images. It is also possible to provide some insight about direction and magnitude of motion from data collected at each angle. Examples of the application with clinical and non-clinical images are shown.

show abstract

“…An example is found in the new filter based on wavelets proposed in (Huerga et al 2017). The improvement in the usual metrics has already been performed.…”

Section: Post-reconstruction Filter Comparing: Phantommentioning

confidence: 99%

Easy blur estimation in PET images including motion corrupted edges

Huerga¹,

Castro²,

Alejo³

et al. 2019

Biomed. Phys. Eng. Express

Self Cite

View full text Add to dashboard Cite

show abstract

“…Huerga et al. used context modeling and spatially adaptive wavelet shrinkage to maintain edges in important regions 13 . Jomaa et al.…”

Section: Introductionmentioning

confidence: 99%

“…12 Huerga et al used context modeling and spatially adaptive wavelet shrinkage to maintain edges in important regions. 13 Jomaa et al presented a new method based on the multiscale and nonlocal means method to reduce noise in dynamic PET sequences. 14 Despite these methods mentioned above can achieve higher visual quality, image filters involve the consideration of several factors which may vary significantly between image processing tasks.…”

mentioning

confidence: 99%

Adaptive 3D noise level‐guided restoration network for low‐dose positron emission tomography imaging

Huang

Zhou

et al. 2023

Interdisciplinary Medicine

View full text Add to dashboard Cite

Many deep learning methods have been proposed to improve the quality of low‐dose PET images (LPET), which usually construct end‐to‐end networks with certain radiation dose inputs. However, these approaches have omitted the noise disparity in PET images, which may differ among manufacturers or populations. Therefore, we tend to exploit these noise differences among PET images to achieve adaptive restoration. We proposed a 3D noise level‐guided PET restoration network for LPET including (1) adaptive noise level‐aware subnetwork and (2) LPET restoration subnetwork. The first subnetwork aims to predict the noise level of the given LPET, while the second subnetwork treats the estimated noise level as a priori information to guide the restoration process from LPET to standard‐dose PET images. Experiments were performed on real human head and neck datasets while the peak signal‐to‐noise ratio and structural similarity index measure were used to evaluate LPET recovery performance. Moreover, we also compared the proposed network with several deep‐learning approaches. Experimental results demonstrate that our network with dual‐stage design can perform adaptive restoration for LPET, yielding better visual and quantitative results. In future work, we attempt to apply our method to other imaging tasks and adapt it for clinical practice.

show abstract

“…However, the wavelet transform suffers from increased computational cost and sub-optimal processing of anisotropic spatiotemporal features (Pogam et al 2013). In addition, non-local means (Dutta et al 2013), local context modelling (Huerga et al 2017), total variation (Yu et al 2017) or basis functions approaches (Reilhac et al 2015) have been used as a means of spatial or temporal regularisation to improve the signal-to-noise in dynamic PET images. However, such approaches may average out or completely eradicate critical temporal information associated with transient changes in the dynamic data, thus hindering or masking the detection of endogenous release of neurotransmitters.…”

Section: Introductionmentioning

confidence: 99%

Denoising non-steady state dynamic PET data using a feed-forward neural network

Angelis

Fuller²,

Gillam

et al. 2021

Phys. Med. Biol.

View full text Add to dashboard Cite

The quality of reconstructed dynamic PET images, as well as the statistical reliability of the estimated pharmacokinetic parameters is often compromised by high levels of statistical noise, particularly at the voxel level. Many denoising strategies have been proposed, both in the temporal and spatial domain, which substantially improve the signal to noise ratio of the reconstructed dynamic images. However, although most filtering approaches are fairly successful in reducing the spatio-temporal inter-voxel variability, they may also average out or completely eradicate the critically important temporal signature of a transient neurotransmitter activation response that may be present in a non-steady state dynamic PET study. In this work, we explore an approach towards temporal denoising of non-steady state dynamic PET images using an artificial neural network, which was trained to identify the temporal profile of a time-activity curve, while preserving any potential activation response. We evaluated the performance of a feed-forward perceptron neural network to improve the signal to noise ratio of dynamic [11C]raclopride activation studies and compared it with the widely used highly constrained back projection (HYPR) filter. Results on both simulated Geant4 Application for Tomographic Emission data of a realistic rat brain phantom and experimental animal data of a freely moving animal study showed that the proposed neural network can efficiently improve the noise characteristics of dynamic data in the temporal domain, while it can lead to a more reliable estimation of voxel-wise activation response in target region. In addition, improvements in signal-to-noise ratio achieved by denoising the dynamic data using the proposed neural network led to improved accuracy and precision of the estimated model parameters of the lp-ntPET model, compared to the HYPR filter. The performance of the proposed denoising approach strongly depends on the amount of noise in the dynamic PET data, with higher noise leading to substantially higher variability in the estimated parameters of the activation response. Overall, the feed-forward network led to a similar performance as the HYPR filter in terms of spatial denoising, but led to notable improvements in terms of temporal denoising, which in turn improved the estimation activation parameters.

show abstract

Denoising of PET images by context modelling using local neighbourhood correlation

Cited by 14 publications

References 21 publications

Easy blur estimation in PET images including motion corrupted edges

Easy blur estimation in PET images including motion corrupted edges

Adaptive 3D noise level‐guided restoration network for low‐dose positron emission tomography imaging

Denoising non-steady state dynamic PET data using a feed-forward neural network

Contact Info

Product

Resources

About