PET image reconstruction using prior information from CT or MRI

Šroubek, Filip; Šorel, Michal; Boldyš, Jiří; Šroubek, Jan

doi:10.1109/icip.2009.5413928

Cited by 3 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been attempts to mitigate partial volume effects in PET images using analytical methods (Alpert et al 2006, Šroubek et al 2009, Erlandsson et al 2012, Guérit et al 2015, Hansen et al 2023, with most traditional approaches involving estimation of the point spread function. These methods are not applicable in the case of collaborative studies involving multiple scanners, or where the point spread function is unknown.…”

Section: Introductionmentioning

confidence: 99%

Neural blind deconvolution for deblurring and supersampling PSMA PET

Sample,

Rahmim,

Uribe

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective: To simultaneously deblur and supersample prostate specific membrane antigen (PSMA) positron emission tomography (PET) images using neural blind deconvolution. Approach: Blind deconvolution is a method of estimating the hypothetical "deblurred" image along with the blur kernel (related to the point spread function) simultaneously. Traditional maximum a posteriori blind deconvolution methods require stringent assumptions and suffer from convergence to a trivial solution. A method of modelling the deblurred image and kernel with independent neural networks, called "neural blind deconvolution" had demonstrated success for deblurring 2D natural images in 2020. In this work, we adapt neural blind deconvolution for PVE correction of PSMA PET images with simultaneous supersampling. We compare this methodology with several interpolation methods, using blind image quality metrics, and test the model's ability to predict kernels by re-running the model after applying artificial "pseudokernels" to deblurred images. The methodology was tested on a retrospective set of 30 prostate patients as well as phantom images containing spherical lesions of various volumes. Main Results: Neural blind deconvolution led to improvements in image quality over other interpolation methods in terms of blind image quality metrics, recovery coefficients, and visual assessment. Predicted kernels were similar between patients, and the model accurately predicted several artificially-applied pseudokernels. Localization of activity in phantom spheres was improved after deblurring, allowing small lesions to be more accurately defined. Significance: The intrinsically low spatial resolution of PSMA PET leads to PVEs which negatively impact uptake quantification in small regions. The proposed method can be used to mitigate this issue, and can be straightforwardly adapted for other imaging modalities.

show abstract

Section: Introductionmentioning

confidence: 99%

Neural blind deconvolution for deblurring and supersampling PSMA PET

Sample,

Rahmim,

Uribe

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…Images were denoised using neural blind deconvolution (Ren et al 2020). Blind deconvolution is the ill-posed mathematical problem of estimating hypothetical denoised images, x, and their associated blur kernel, k, which convolve to yield the original image, y = x * k. This method is particularly useful in situations where spatial resolution and precision of signal localization is low, hence many studies have attempted to employ it for positron emission tomography (PET) (Alpert et al 2006, Lee et al 2008, Šroubek et al 2009, Erlandsson et al 2012, Guérit et al 2015. The use of a single kernel for entire images is an approximation, as it has been found (Levin et al 2009) that the shift-invariant assumption for the blur kernel is often incorrect.…”

Section: Denoisingmentioning

confidence: 99%

Image denoising and model-independent parameterization for IVIM MRI

Sample,

Wu,

Clark

2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective: To improve intravoxel incoherent motion imaging (IVIM) magnetic resonance Imaging (MRI) quality using a new image denoising technique and model-independent parameterization of the signal versus b-value curve. Approach: IVIM images were acquired for 13 head-and-neck patients prior to radiotherapy. Post-radiotherapy scans were also acquired for five patients. Images were denoised prior to parameter fitting using neural blind deconvolution, a method of solving the mathematical problem of blind deconvolution using neural networks. The signal decay curve was then quantified in terms of several area under the curve (AUC) parameters. Improvements in image quality were assessed using blind image quality metrics, total variation (TV), and the strength of correlations between IVIM parameters in parotid glands with radiotherapy dose levels. The accuracy of blur kernel predictions was assessed by the ability to recover artificial "pseudokernels" which had been applied to denoised images. AUC parameters were compared with apparent diffusion coefficient (ADC), biexponential, and triexponential model parameters in terms of their correlations with dose, contrast-to-noise (CNR) ratios inside and outside parotid glands, and their relative importance as determined via principal component analysis.Main Results: Image denoising improved blind image quality metrics, smoothed the signal versus b-value curve, and strengthened correlations between IVIM parameters and dose. Image TV was reduced and parameter CNRs generally increased following denoising. AUC parameter changes had higher correlations with dose and higher relative importance than traditional IVIM parameters. Significance: IVIM parameters have high variability in the literature and perfusion-related parameters are difficult to interpret. Describing the signal versus b-value curve with model-independent parameters like the AUC and preprocessing images with denoising techniques could potentially benefit IVIM image parameterization in terms of reproducibility and functional utility.

show abstract

“…Post-reconstruction restoration techniques are more adapted to clinical use since only reconstructed images are generally available. Nowadays, existing approaches are dedicated to denoising, deblurring, or combining both steps [2,3,4,5]. Most of the approaches that include deblurring use an empirically estimated PSF.…”

Section: Motivationmentioning

confidence: 99%

“…Anatomical information can be useful to regularize such an ill-posed inverse problem [4]. Due to its perfect dilution in the kidneys, 18 FDG accumulates uniformly in the patient bladder with a high concentration (see Fig.…”

Section: Contributionsmentioning

confidence: 99%

“…As commonly done in the literature [4,9,10], we assume that images analyzed in this work are composed by slowly varying areas separated by sharp boundaries corresponding to tissue interfaces. Therefore, the inverse problem can be further regularized by promoting small Total-Variation norm (denoted u TV ), which corresponds to the 1 -norm of the magnitude of the gradient of u ∈ R N [10].…”

Section: Blind Deconvolutionmentioning

confidence: 99%

See 1 more Smart Citation

Blind Deconvolution of PET Images using Anatomical Priors

Guérit,

González,

Bol

et al. 2016

Preprint

View full text Add to dashboard Cite

Images from positron emission tomography (PET) provide metabolic information about the human body. They present, however, a spatial resolution that is limited by physical and instrumental factors often modeled by a blurring function. Since this function is typically unknown, blind deconvolution (BD) techniques are needed in order to produce a useful restored PET image. In this work, we propose a general BD technique that restores a low resolution blurry image using information from data acquired with a high resolution modality (e.g., CT-based delineation of regions with uniform activity in PET images). The proposed BD method is validated on synthetic and actual phantoms.

show abstract

PET image reconstruction using prior information from CT or MRI

Cited by 3 publications

References 9 publications

Neural blind deconvolution for deblurring and supersampling PSMA PET

Neural blind deconvolution for deblurring and supersampling PSMA PET

Image denoising and model-independent parameterization for IVIM MRI

Blind Deconvolution of PET Images using Anatomical Priors

Contact Info

Product

Resources

About