Potential benefits of incorporating energy information when estimating attenuation from PET data

Brusaferri, Ludovica; Bousse, Alexandre; Efthimiou, Nikos; Emond, Elise; Atkinson, David; Ourselin, Sébastien; Hutton, Brian F.; Arridge, Simon R.; Thielemans, Kris

doi:10.1109/nssmic.2017.8532765

Cited by 12 publications

(15 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further improvement in this direction will be to train the network using a full-size intermediate space to map each anatomical section, such as the intermediate representations presented in [21] and [22]. The current sCT generation can also be used as prior on attenuation reconstruction techniques such as the maximum-likelihood reconstruction of attenuation and activity (MLAA) [23,24] single scatter modeling [25] . These techniques can potentially eliminate artefacts from the generated attenuation maps, such as the CT contrast in the stomach observed in Fig.…”

Section: Discussionmentioning

confidence: 99%

Whole Body Positron Emission Tomography Attenuation Correction Map Synthesizing using 3D Deep Generative Adversarial Networks

Colmeiro¹,

Verrastro²,

Minsky³

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: The correction of attenuation effects in Positron Emission Tomography (PET) imaging is fundamental to obtain a correct radiotracer distribution. However direct measurement of this attenuation map is not error-free and normally results in additional ionization radiation dose to the patient. Here, we propose to obtain the whole body attenuation map using a 3D U-Net generative adversarial network. The network is trained to learn the mapping from non attenuation corrected 18-F-fluorodeoxyglucose PET images to a synthetic Computerized Tomography (sCT) and also to label the input voxel tissue. The sCT image is further refined using an adversarial training scheme to recover higher frequency details and lost structures using context information. This work is trained and tested on public available datasets, containing several PET images from different scanners with different radiotracer administration and reconstruction modalities. The network is trained with 108 samples and validated on 10 samples.Results: The sCT generation was tested on 133 samples from 8 distinct datasets. The resulting mean absolute error of the network is 103 ± 18 HU and a peak signal to noise ratio of 18.6 ± 1.5 dB. The generated images show good correlation with the unknown structural information.Conclusions: The proposed deep learning topology is capable of generating whole body attenuation maps from uncorrected PET image data. Moreover, the method accuracy holds in the presence of data form multiple sources and modalities and is trained on publicly available datasets.

show abstract

Section: Discussionmentioning

confidence: 99%

Whole Body Positron Emission Tomography Attenuation Correction Map Synthesizing using 3D Deep Generative Adversarial Networks

Colmeiro¹,

Verrastro²,

Minsky³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Thanks to STIR's, modular structure, all other features present in the library such as Time-of-Flight reconstruction [11], [12], regularised reconstruction [13]- [16], scatter [17], [18], motion correction [19], [20] and parametric imaging [21], resolution recovery [22] e.t.c., would be immediately available for Total Body PET scanners.…”

Section: Future Workmentioning

confidence: 99%

Preliminary investigation of the impact of Axial Ring Splitting on Image Quality for the Cost Reduction of Total-Body PET

Efthimiou

Whitehead

Stockhoff

et al. 2019

2019 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC)

View full text Add to dashboard Cite

Recently, the first TB-PET scanner was unveiled and the initial results were nevertheless impressive. However, the cost of a TB-PET scanner is prohibiting for many institutions around the globe. Therefore here we investigate a cost reduction strategy incorporating a flexible detector arrangement. The proposed arrangement increases the axial field of view while keeping the overall cost at lower levels. We propose the axial ring splitting, which separates the full rings, of a compact PET scanner, to an expanded scanner with rings having only even or only odd numbered detectors. In this paper some preliminary performance results using Monte Carlo simulations, will be presented. In this comparison three configurations were considered (a) full rings PET (b) half-split rings TB-PET (c) full-split rings TB-PET. In addition in this investigation the effects of a varying coincidence window are demonstrated. The preliminary results suggest that Config.A demonstrated the highest Noise Equivalent count rate using either a fixed or a varying coincidence window. The main reasons were the absence of gaps and better handling of background radiation. However, reconstructed images for a single bed, from a whole body acquisition, suggested that due to the longer single bed acquisition of the full-split rings geometry the images present better noise properties.

show abstract

“…We currently assume that g sc UU , g sc UL and g sc LU contain single scatter events only. We do not use the g LL data as it contains very few single scatter events [3].…”

Section: A Multiple Energy Window Datamentioning

confidence: 99%

“…The emission image is reconstructed with a Maximum Likelihood (ML) estimator from UU data, whilst the attenuation image is obtained with the MLTR-EB algorithm [3] from the other energy window pairs (UL, LU). Both likelihoods use a Poisson model.…”

Section: B Mlaa-eb Optimisation Algorithmmentioning

confidence: 99%

“…In previous work, we demonstrated that the finite energy resolution of PET detectors can be efficiently modelled when using multiple energy window measurements and that it is possible to estimate the attenuation distribution of the object from such data if the emission image is known [3]. This paper explores the feasibility of incorporating a 3D probabilistic scatter model into a joint reconstruction scheme, without having to resort to the assumption of the absence of scatter in the photopeak window.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Maximum-likelihood estimation of emission and attenuation images in 3D PET from multiple energy window measurements

Brusaferri

Bousse

Tsai

et al. 2018

2018 IEEE Nuclear Science Symposium and Medical Imaging Conference Proceedings (NSS/MIC)

Self Cite

View full text Add to dashboard Cite

This study explores the feasibility of incorporating energy information into a maximum-likelihood reconstruction of activity and attenuation (MLAA) framework. The attenuation and activity distributions were reconstructed from multiple energy window data, and a scatter function was added to the system model of the algorithm. The proposed energy-based method (MLAA-EB) was evaluated with simulated 3D phantom data, using the geometry and characteristics of a Siemens mMR PET-MR scanner. Results showed that the proposed algorithm is able to compensate for errors in the activity image caused by the incorrect assignment of attenuation values to the segmented MR. This is effective for small objects only, for large objects further solutions need to be found.

show abstract

Potential benefits of incorporating energy information when estimating attenuation from PET data

Cited by 12 publications

References 17 publications

Whole Body Positron Emission Tomography Attenuation Correction Map Synthesizing using 3D Deep Generative Adversarial Networks

Whole Body Positron Emission Tomography Attenuation Correction Map Synthesizing using 3D Deep Generative Adversarial Networks

Preliminary investigation of the impact of Axial Ring Splitting on Image Quality for the Cost Reduction of Total-Body PET

Maximum-likelihood estimation of emission and attenuation images in 3D PET from multiple energy window measurements

Contact Info

Product

Resources

About