Model-Based Deep Learning PET Image Reconstruction Using Forward-Backward Splitting Expectation-Maximization

• Published in: IEEE transactions on radiation and plasma medical sciences Vol. 5; no. 1; pp. 54 - 64
• Main Authors: Mehranian, Abolfazl, Reader, Andrew J.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Brain; Brain modeling; Computer simulation; Datasets; Deep learning; Deep learning (DL); Fields (mathematics); Image processing; Image reconstruction; Machine learning; Maximization; Medical imaging; MRI; Neural networks; Neuroimaging; Noise reduction; Optimization; Positron emission; Positron emission tomography; positron emission tomography (PET); Regularization; Splitting; Tomography; Training; image reconstruction; Deep learning (DL); MRI; positron emission tomography (PET)

We propose a forward-backward splitting algorithm to integrate deep learning into maximum- a-posteriori (MAP) positron emission tomography (PET) image reconstruction. The MAP reconstruction is split into regularization, expectation-maximization (EM), and a weighted fusion. For regularization, the us...