Incorporation of anatomical MRI knowledge for enhanced mapping of brain metabolism using functional PET.

Functional positron emission tomography (fPET) imaging using continuous infusion of [18F]-fluorodeoxyglucose (FDG) is a novel neuroimaging technique to track dynamic glucose utilization in the brain. In comparison to conventional static or dynamic bolus PET, fPET maintains a sustained supply of glucose in the blood plasma which improves sensitivity to measure dynamic glucose changes in the brain, and enables mapping of dynamic brain activity in task-based and resting-state fPET studies. However, there is a trade-off between temporal resolution and spatial noise due to the low concentration of FDG and the limited sensitivity of multi-ring PET scanners. Images from fPET studies suffer from partial volume errors and residual scatter noise that may cause the cerebral metabolic functional maps to be biased. Gaussian smoothing filters used to denoise the fPET images are suboptimal, as they introduce additional partial volume errors. In this work, a post-processing framework based on a magnetic resonance (MR) Bowsher-like prior was used to improve the spatial and temporal signal to noise characteristics of the fPET images. The performance of the MR guided method was compared with conventional denosing methods using both simulated and in vivo task fPET datasets. The results demonstrate that the MR-guided fPET framework denoises the fPET images and improves the partial volume correction, consequently enhancing the sensitivity to identify brain activation, and improving the anatomical accuracy for mapping changes of brain metabolism in response to a visual stimulation task. The framework extends the use of functional PET to investigate the dynamics of brain metabolic responses for faster presentation of brain activation tasks, and for applications in low dose PET imaging.

Augmented deep learning model for improved quantitative accuracy of MR-based PET attenuation correction in PSMA PET-MRI prostate imaging.

PURPOSE: Estimation of accurate attenuation maps for whole-body positron emission tomography (PET) imaging in simultaneous PET-MRI systems is a challenging problem as it affects the quantitative nature of the modality. In this study, we aimed to improve the accuracy of estimated attenuation maps from MRI Dixon contrast images by training an augmented generative adversarial network (GANs) in a supervised manner. We augmented the GANs by perturbing the non-linear deformation field during image registration between MRI and the ground truth CT images. METHODS: We acquired the CT and the corresponding PET-MR images for a cohort of 28 prostate cancer patients. Data from 18 patients (2160 slices and later augmented to 270,000 slices) was used for training the GANs and others for validation. We calculated the error in bone and soft tissue regions for the AC µ-maps and the reconstructed PET images. RESULTS: For quantitative analysis, we use the average relative absolute errors and validate the proposed technique on 10 patients. The DL-based MR methods generated the pseudo-CT AC µ-maps with an accuracy of 4.5% more than standard MR-based techniques. Particularly, the proposed method demonstrates improved accuracy in the pelvic regions without affecting the uptake values. The lowest error of the AC µ-map in the pelvic region was 1.9% for µ-mapGAN + aug compared with 6.4% for µ-mapdixon, 5.9% for µ-mapdixon + bone, 2.1% for µ-mapU-Net and 2.0% for µ-mapU-Net + aug. For the reconstructed PET images, the lowest error was 2.2% for PETGAN + aug compared with 10.3% for PETdixon, 8.7% for PETdixon + bone, 2.6% for PETU-Net and 2.4% for PETU-Net + aug.. CONCLUSION: The proposed technique to augment the training datasets for training of the GAN results in improved accuracy of the estimated µ-map and consequently the PET quantification compared to the state of the art.

Forward Model and Deep Learning Based Iterative Deconvolution for Robust Dynamic CT Perfusion.

Perfusion maps obtained from low-dose computed tomography (CT) data suffer from poor signal to noise ratio. To enhance the quality of the perfusion maps, several works rely on denoising the low-dose CT (LD-CT) images followed by conventional regularized deconvolution. Recent works employ deep neural networks (DNN) for learning a direct mapping between the noisy and the clean perfusion maps ignoring the convolution-based forward model. DNN-based methods are not robust to practical variations in the data that are seen in real-world applications such as stroke. In this work, we propose an iterative framework that combines the perfusion forward model with a DNN-based regularizer to obtain perfusion maps directly from the LD-CT dynamic data. To improve the robustness of the DNN, we leverage the anatomical information from the contrast-enhanced LD-CT images to learn the mapping between low-dose and standard-dose perfusion maps. Through empirical experiments, we show that our model is robust both qualitatively and quantitatively to practical perturbations in the data.

Towards lower-dose PET using physics-based uncertainty-aware multimodal learning with robustness to out-of-distribution data.

Radiation exposure in positron emission tomography (PET) imaging limits its usage in the studies of radiation-sensitive populations, e.g., pregnant women, children, and adults that require longitudinal imaging. Reducing the PET radiotracer dose or acquisition time reduces photon counts, which can deteriorate image quality. Recent deep-neural-network (DNN) based methods for image-to-image translation enable the mapping of low-quality PET images (acquired using substantially reduced dose), coupled with the associated magnetic resonance imaging (MRI) images, to high-quality PET images. However, such DNN methods focus on applications involving test data that match the statistical characteristics of the training data very closely and give little attention to evaluating the performance of these DNNs on new out-of-distribution (OOD) acquisitions. We propose a novel DNN formulation that models the (i) underlying sinogram-based physics of the PET imaging system and (ii) the uncertainty in the DNN output through the per-voxel heteroscedasticity of the residuals between the predicted and the high-quality reference images. Our sinogram-based uncertainty-aware DNN framework, namely, suDNN, estimates a standard-dose PET image using multimodal input in the form of (i) a low-dose/low-count PET image and (ii) the corresponding multi-contrast MRI images, leading to improved robustness of suDNN to OOD acquisitions. Results on in vivo simultaneous PET-MRI, and various forms of OOD data in PET-MRI, show the benefits of suDNN over the current state of the art, quantitatively and qualitatively.

Joint PET-MRI image reconstruction using a patch-based joint-dictionary prior.

For simultaneous positron-emission-tomography and magnetic-resonance-imaging (PET-MRI) systems, while early methods relied on independently reconstructing PET and MRI images, recent works have demonstrated improvement in image reconstructions of both PET and MRI using joint reconstruction methods. The current state-of-the-art joint reconstruction priors rely on fine-scale PET-MRI dependencies through the image gradients at corresponding spatial locations in the PET and MRI images. In the general context of image restoration, compared to gradient-based models, patch-based models (e.g., sparse dictionaries) have demonstrated better performance by modeling image texture better. Thus, we propose a novel joint PET-MRI patch-based dictionary prior that learns inter-modality higher-order dependencies together with intra-modality textural patterns in the images. We model the joint-dictionary prior as a Markov random field and propose a novel Bayesian framework for joint reconstruction of PET and accelerated-MRI images, using expectation maximization for inference. We evaluate all methods on simulated brain datasets as well as on in vivo datasets. We compare our joint dictionary prior with the recently proposed joint priors based on image gradients, as well as independently applied patch-based priors. Our method demonstrates qualitative and quantitative improvement over the state of the art in both PET and MRI reconstructions.