Magnetic resonance image synthesis through patch regression

Abstract

Magnetic resonance imaging (MRI) is widely used for analyzing human brain structure and function. MRI is extremely versatile and can produce different tissue contrasts as required by the study design. For reasons such as patient comfort, cost, and improving technology, certain tissue contrasts for a cohort analysis may not have been acquired during the imaging session. This missing pulse sequence hampers consistent neuroanatomy research. One possible solution is to synthesize the missing sequence. This paper proposes a data-driven approach to image synthesis, which provides equal, if not superior synthesis compared to the state-of-the-art, in addition to being an order of magnitude faster. The synthesis transformation is done on image patches by a trained bagged ensemble of regression trees. Validation was done by synthesizing <i>T</i>₂-weighted contrasts from <i>T</i>₁-weighted scans, for phantoms and real data. We also synthesized 3 Tesla <i>T</i>₁-weighted magnetization prepared rapid gradient echo (MPRAGE) images from 1.5 Tesla MPRAGEs to demonstrate the generality of this approach.