Enhanced PET/MRI reconstruction via dichromatic interpolation of domain-translated zero-dose PET

Rajagopal, Abhejit; Dwork, Nicholas; Hope, Thomas A.; Larson, Peder E. Z.

doi:10.1117/12.2580915

Cited by 7 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The joint-sparsity approach excels in this setting since it does not enforce that both modalities (EO and SAR) match in the content of the target-scene, but only that their structure in the transform domain are similar. 5 This enables strong data consistency not provided by conventional image-fusion techniques.…”

Section: Discussionmentioning

confidence: 99%

“…Specifically, we introduce a joint-sparsity term that seeks to capture the complementary structural information shared between EO-derived 3D models and SAR via a sparsifying transform of the 3D image domain (here we utilize db4 Daubechies wavelets). The basic idea of our approach is to utilize the sparsity patterns of historical or concurrent EO 3D models to help guide the 3D image solution if and when they provide complementary information not captured by the data-consistency terms 5 This is an important feature of our method that makes it distinct from modality-fusion algorithms, 6,7 since our method allows utilizing 3D EO priors even when they are not up-to-date, without sacrificing the information content provided by the radar measurements.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced compressed sensing 3D SAR imaging via cross-modality EO-SAR joint-sparsity priors

Rajagopal

Hilton

Boutte

et al. 2023

Algorithms for Synthetic Aperture Radar Imagery XXX

View full text Add to dashboard Cite

We introduce a compressed sensing technique for leveraging prior electro-optic (EO) imagery to improve 3D synthetic aperture radar (SAR) imaging performance. Specifically, we build on existing iterative reconstruction algorithms by guiding the reconstruction process with a joint-sparsity regularization term that captures the complementary structural information shared between EO and SAR via a sparsifying transform in the 3D image domain. We demonstrate this approach using the wavelet transform, the non-uniform Fast-Fourier transform (NUFFT), and optimizers built on autograd utilizing the 2004 AFRL Gotcha SAR dataset, with complementary EO imagery collected from the 2013 Minor Area Motion Imagery (MAMI) collection and more recent (2016) satellite collections over the same area. Results indicate significant improvements in 2D and 3D imaging performance via incorporation of the cross-modality EO prior, which we attribute to the convex problem formulation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Enhanced compressed sensing 3D SAR imaging via cross-modality EO-SAR joint-sparsity priors

Rajagopal

Hilton

Boutte

et al. 2023

Algorithms for Synthetic Aperture Radar Imagery XXX

View full text Add to dashboard Cite

show abstract

“…The sbPET image may be deployed as a general tool in other neuroimaging tasks and standard clinical routines. Rajagopal et al (2021) proposed the use of a deep-domain translated image as a prior in the reconstruction of PET images from sinograms. More specifically, a synthetic [ 18 F]FDG-PET could impose sparsity constraints on the reconstruction problem to allow recovery of noisy low-dose PET/MRI.…”

Section: Discussionmentioning

confidence: 99%

A zero-dose synthetic baseline for the personalized analysis of [18F]FDG-PET: Application in Alzheimer’s disease

Hinge

Henriksen²,

Lindberg³

et al. 2022

Front. Neurosci.

View full text Add to dashboard Cite

PurposeBrain 2-Deoxy-2-[18F]fluoroglucose ([18F]FDG-PET) is widely used in the diagnostic workup of Alzheimer’s disease (AD). Current tools for uptake analysis rely on non-personalized templates, which poses a challenge as decreased glucose uptake could reflect neuronal dysfunction, or heterogeneous brain morphology associated with normal aging. Overcoming this, we propose a deep learning method for synthesizing a personalized [18F]FDG-PET baseline from the patient’s own MRI, and showcase its applicability in detecting AD pathology.MethodsWe included [18F]FDG-PET/MRI data from 123 patients of a local cohort and 600 patients from ADNI. A supervised, adversarial model with two connected Generative Adversarial Networks (GANs) was trained on cognitive normal (CN) patients with transfer-learning to generate full synthetic baseline volumes (sbPET) (192 × 192 × 192) which reflect healthy uptake conditioned on brain anatomy. Synthetic accuracy was measured by absolute relative %-difference (Abs%), relative %-difference (RD%), and peak signal-to-noise ratio (PSNR). Lastly, we deployed the sbPET images in a fully personalized method for localizing metabolic abnormalities.ResultsThe model achieved a spatially uniform Abs% of 9.4%, RD% of 0.5%, and a PSNR of 26.3 for CN subjects. The sbPET images conformed to the anatomical information dictated by the MRI and proved robust in presence of atrophy. The personalized abnormality method correctly mapped the pathology of AD subjects while showing little to no anomalies for CN subjects.ConclusionThis work demonstrated the feasibility of synthesizing fully personalized, healthy-appearing [18F]FDG-PET images. Using these, we showcased a promising application in diagnosing AD, and theorized the potential value of sbPET images in other neuroimaging routines.

show abstract

“…In another vein, synthetic PET can also be used to directly improve image reconstruction algorithms themselves, e.g. by generation of an deep learning prior image that can help regularize PET image reconstruction [45]. These applications provide a strong motivation for future work in curating large databases of PET/MRI with multiple MRI contrasts and PET radiotracer images, which could mirror and complement the impact of other synthetic MRI [46], [47].…”

Section: Future Workmentioning

confidence: 99%

Synthetic PET via Domain Translation of 3-D MRI

Rajagopal¹,

Natsuaki

Wangerin³

et al. 2023

IEEE Trans. Radiat. Plasma Med. Sci.

View full text Add to dashboard Cite

Historically, patient datasets have been used to develop and validate various reconstruction algorithms for PET/MRI and PET/CT. To enable such algorithm development, without the need for acquiring hundreds of patient exams, in this paper we demonstrate a deep learning technique to generate synthetic but realistic whole-body PET sinograms from abundantly-available whole-body MRI. Specifically, we use a dataset of 56 18 F-FDG-PET/MRI exams to train a 3D residual UNet to predict physiologic PET uptake from whole-body T1-weighted MRI. In training we implemented a balanced loss function to generate realistic uptake across a large dynamic range and computed losses along tomographic lines of response to mimic the PET acquisition. The predicted PET images are forward projected to produce synthetic PET time-of-flight (ToF) sinograms that can be used with vendor-provided PET reconstruction algorithms, including using CT-based attenuation correction (CTAC) and MR-based attenuation correction (MRAC). The resulting synthetic data recapitulates physiologic 18 F-FDG uptake, e.g. high uptake localized to the brain and bladder, as well as uptake in liver, kidneys, heart and muscle. To simulate abnormalities with high uptake, we also insert synthetic lesions. We demonstrate that this synthetic PET data can be used interchangeably with real PET data for the PET quantification task of comparing CT and MRbased attenuation correction methods, achieving ≤ 7.6% error in mean-SUV compared to using real data. These results together show that the proposed synthetic PET data pipeline can be reasonably used for development, evaluation, and validation of PET/MRI reconstruction methods.

show abstract

Enhanced PET/MRI reconstruction via dichromatic interpolation of domain-translated zero-dose PET

Cited by 7 publications

References 0 publications

Enhanced compressed sensing 3D SAR imaging via cross-modality EO-SAR joint-sparsity priors

Enhanced compressed sensing 3D SAR imaging via cross-modality EO-SAR joint-sparsity priors

A zero-dose synthetic baseline for the personalized analysis of [18F]FDG-PET: Application in Alzheimer’s disease

Synthetic PET via Domain Translation of 3-D MRI

Contact Info

Product

Resources

About