Learning Two-factor Representation for Magnetic Resonance Image Super-resolution
This work addresses the problem of high-resolution MRI acquisition for medical imaging by providing an unsupervised super-resolution solution, though it appears incremental as it builds on existing representation learning approaches.
The paper tackles the challenge of learning continuous volumetric representations for MRI super-resolution without high-resolution supervision, proposing a two-factor representation method that achieves state-of-the-art performance on datasets like BraTS 2019 and MSSEG 2016, with superior visual fidelity and robustness in large up-sampling scales.
Magnetic Resonance Imaging (MRI) requires a trade-off between resolution, signal-to-noise ratio, and scan time, making high-resolution (HR) acquisition challenging. Therefore, super-resolution for MR image is a feasible solution. However, most existing methods face challenges in accurately learning a continuous volumetric representation from low-resolution image or require HR image for supervision. To solve these challenges, we propose a novel method for MR image super-resolution based on two-factor representation. Specifically, we factorize intensity signals into a linear combination of learnable basis and coefficient factors, enabling efficient continuous volumetric representation from low-resolution MR image. Besides, we introduce a coordinate-based encoding to capture structural relationships between sparse voxels, facilitating smooth completion in unobserved regions. Experiments on BraTS 2019 and MSSEG 2016 datasets demonstrate that our method achieves state-of-the-art performance, providing superior visual fidelity and robustness, particularly in large up-sampling scale MR image super-resolution.