Photon-counting CT (PCCT) is powerful for spectral imaging and material decomposition but produces noisy weighted filtered backprojection (wFBP) reconstructions. Although iterative reconstruction effectively denoises these images, it requires extensive computation time. To overcome this limitation, we propose a deep learning (DL) model, UnetU, which quickly estimates from wFBP. Utilizing 2D U-n...

Detecting cancerous lesion is an important task in positron emission tomography (PET). Bayesian methods based on the maximum a posteriori principle (also called penalized maximum likelihood methods) have been developed to deal with the low signal to noise ratio in the emission data. Similar to the filter cut-off frequency in the filtered backprojection method, the prior parameters in Bayesian r...

PURPOSE The goal of this paper is to extend our recently developed FBP (filtered backprojection) algorithm, which has the same characteristics of an iterative Landweber algorithm, to an FBP algorithm with the same characteristics of an iterative MAP (maximum a posteriori) algorithm. The newly developed FBP algorithm also works when the angular sampling interval is not uniform. The projection no...

Region of interest (ROI) quantitation is an important task in emission tomography (e.g., positron emission tomography and single photon emission computed tomography). It is essential for exploring clinical factors such as tumor activity, growth rate, and the efficacy of therapeutic interventions. Bayesian methods based on the maximum a posteriori principle (or called penalized maximum likelihoo...

INTRODUCTION: Displacement Encoding with Stimulated Echoes (DENSE) has been developed for quantifying regional myocardial strain based on phase contrast images acquired during systole (1). Recent modifications to the original method (2,3) utilize RF phase cycling for suppressing the stimulated anti-echo and the unencoded FID signals. Despite the increased SNR due to the averaging employed, this...

INTRODUCTION – Typical fMRI acquisitions cannot reveal great detail about activated brain regions due to poor image resolution. At present, 64x64 voxels per slice is still the most commonly used acquisition matrix size for fMRI studies, leading to an in-plane resolution of 3.75 mm with FOV = 24 cm. Increasing spatial resolution is very time consuming, e.g. doubling in-plane resolution increases...

Background A promising technique to measure blood flow is timeresolved three-dimensional phase contrast MRI (PCMRI). In small structures as the Circle of Willis (CoW), the resolution of the measurement needs to be high (< 1 mm). Image quality may be compromised when SNR decreases with increasing resolution which leads to blood flow direction uncertainty and flow quantification inaccuracies. To ...