Quantitative evaluation of image quality restoration for short-acquisition brain PET using deep learning models and a dedicated three-dimensional-printed striatum phantom.

The phantom was fabricated with copper filament, filled with Fluorine-18, and imaged using a clinical digital positron emission tomography/computed tomography scanner.

A total of 500 paired datasets, consisting of 1-min input and 10-min reference images, were divided into training, validation, and test sets in an 8:1:1 ratio.

Both models substantially improved RMSE, peak signal-to-noise ratio, universal quality index, learned perceptual image patch similarity, and contrast-to-noise ratio compared with the 1-min input images (p < 0.001).