Deep filter bank regression for super-resolution of anisotropic MR brain images

TL;DR

This paper introduces a novel filter bank-based approach for super-resolution of anisotropic MR brain images, explicitly estimating missing high-frequency information without external data, improving results especially in slice gap scenarios.

Contribution

It reformulates super-resolution as a perfect reconstruction filter bank problem and proposes a two-stage method to directly estimate missing filters and coefficients.

Findings

Improved super-resolution in slice gap scenarios.

Explicit estimation of missing high-frequency information.

No reliance on external training data.

Abstract

In 2D multi-slice magnetic resonance (MR) acquisition, the through-plane signals are typically of lower resolution than the in-plane signals. While contemporary super-resolution (SR) methods aim to recover the underlying high-resolution volume, the estimated high-frequency information is implicit via end-to-end data-driven training rather than being explicitly stated and sought. To address this, we reframe the SR problem statement in terms of perfect reconstruction filter banks, enabling us to identify and directly estimate the missing information. In this work, we propose a two-stage approach to approximate the completion of a perfect reconstruction filter bank corresponding to the anisotropic acquisition of a particular scan. In stage 1, we estimate the missing filters using gradient descent and in stage 2, we use deep networks to learn the mapping from coarse coefficients to detail coefficients. In addition, the proposed formulation does not rely on external training data, circumventing the need for domain shift correction. Under our approach, SR performance is improved particularly in "slice gap" scenarios, likely due to the constrained solution space imposed by the framework.