Search papers, labs, and topics across Lattice.
This paper introduces Anatomy-Guided Gaussian-Parameter Warping with PVE-Balanced Reconstruction (AGW-PBR), a novel method for improving super-resolution in brain MRI by addressing the partial-volume effect (PVE) through a training-time objective that emphasizes tissue transitions. By integrating low-resolution Sobel guidance and soft latent-basis assignment, AGW-PBR enhances the fidelity of reconstructed images, particularly in tissue-interface regions, while maintaining strong performance on PVE-free datasets. The method demonstrates significant improvements in full-image reconstruction quality across multiple scales, particularly at 4x magnification, highlighting the effectiveness of tissue-mixture entropy weighting in MRI super-resolution tasks.
AGW-PBR achieves superior brain MRI super-resolution by effectively addressing the partial-volume effect, enhancing fidelity in tissue transitions that traditional methods overlook.
Full-image objectives in brain magnetic resonance imaging (MRI) super-resolution (SR) can underweight tissue-transition regions affected by the partial-volume effect (PVE), as these regions occupy only a small fraction of the image. Binary boundaries also do not capture the continuous mixture of cerebrospinal fluid, gray matter, and white matter within a voxel. We propose Anatomy-Guided Gaussian-Parameter Warping with PVE-Balanced Reconstruction (AGW-PBR), which combines a low-resolution (LR)-only reconstruction backbone with a training-time objective that emphasizes tissue transitions. The backbone integrates LR-derived Sobel guidance, soft latent-basis assignment, and bounded grid-anchored residual warping. Fixed, quality-controlled tissue fractions derived from registered T1/T2/PD IXI images are converted into tissue-mixture entropy, which defines mean-normalized reconstruction weights within validated PVE support. These sidecars are used only during training, and inference requires only the LR image. AGW-PBR is evaluated on T2-weighted IXI images at 2x, 4x, and 6x using three seeds and subject-level paired analyses. At 4x, test-only SynthSeg masks independently assess reconstruction in tissue-interface and non-interface regions. Targeted ablations examine valid-support supervision, spatially aligned entropy weighting, and soft latent assignment. The AGW-backbone is also trained from scratch on fastMRI at 4x without PVE supervision. AGW-PBR improves full-image reconstruction across the tested IXI scales and regional fidelity at 4x, while the PVE-free backbone retains strong performance on fastMRI. These findings support tissue-mixture entropy weighting for partial-volume-aware brain MRI SR.
