Multi-scale MRI reconstruction via dilated ensemble networks
This work improves MRI reconstruction for medical imaging by enhancing detail recovery and efficiency, though it is incremental as it builds on existing multi-scale and complex-valued approaches.
The paper tackled the problem of MRI reconstruction by addressing aliasing artefacts and fine detail loss in existing networks, introducing a multi-scale network using dilated convolutions that outperformed state-of-the-art methods while being three times more efficient.
As aliasing artefacts are highly structural and non-local, many MRI reconstruction networks use pooling to enlarge filter coverage and incorporate global context. However, this inadvertently impedes fine detail recovery as downsampling creates a resolution bottleneck. Moreover, real and imaginary features are commonly split into separate channels, discarding phase information particularly important to high frequency textures. In this work, we introduce an efficient multi-scale reconstruction network using dilated convolutions to preserve resolution and experiment with a complex-valued version using complex convolutions. Inspired by parallel dilated filters, multiple receptive fields are processed simultaneously with branches that see both large structural artefacts and fine local features. We also adopt dense residual connections for feature aggregation to efficiently increase scale and the deep cascade global architecture to reduce overfitting. The real-valued version of this model outperformed common reconstruction architectures as well as a state-of-the-art multi-scale network whilst being three times more efficient. The complex-valued network yielded better qualitative results when more phase information was present.