Deep filter bank regression for super-resolution of anisotropic MR brain images
This work addresses the challenge of enhancing resolution in medical imaging for brain scans, offering a domain-specific incremental improvement.
The paper tackles the problem of super-resolution for anisotropic MR brain images by reframing it in terms of perfect reconstruction filter banks to explicitly estimate missing high-frequency information, resulting in improved performance in 'slice gap' scenarios without relying on external training data.
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.