DULDA: Dual-domain Unsupervised Learned Descent Algorithm for PET image reconstruction
This addresses the impracticality of obtaining labeled data for PET scans due to long scanning times and high radiation exposure, offering an incremental improvement in unsupervised reconstruction.
The paper tackles the problem of PET image reconstruction without needing high-quality training labels by proposing a dual-domain unsupervised method, achieving superior performance compared to existing methods like MLEM, EM-TV, and DIP.
Deep learning based PET image reconstruction methods have achieved promising results recently. However, most of these methods follow a supervised learning paradigm, which rely heavily on the availability of high-quality training labels. In particular, the long scanning time required and high radiation exposure associated with PET scans make obtaining this labels impractical. In this paper, we propose a dual-domain unsupervised PET image reconstruction method based on learned decent algorithm, which reconstructs high-quality PET images from sinograms without the need for image labels. Specifically, we unroll the proximal gradient method with a learnable l2,1 norm for PET image reconstruction problem. The training is unsupervised, using measurement domain loss based on deep image prior as well as image domain loss based on rotation equivariance property. The experimental results domonstrate the superior performance of proposed method compared with maximum likelihood expectation maximazation (MLEM), total-variation regularized EM (EM-TV) and deep image prior based method (DIP).