On the public ReMIND dataset, a systematic benchmark of six synthesis models across 48 experiments finds LPIPS correlates with downstream segmentation utility while SSIM does not, with SynDiff-2.5D performing best.
IEEE Transactions on Medical Imaging 41(10), 2598–2614 (2022)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
HA-DSB uses a diffusion Schrödinger bridge with vision-language model region embeddings and PET-guided noise modulation to translate whole-body MRI while preserving lesion fidelity.
FGSB is a two-stage neural Schrödinger bridge that generates missing MRI modalities from limited paired data and preserves lesions via expert priors.
citing papers explorer
-
A Systematic Benchmark of Intraoperative Ultrasound-to-MR Synthesis for Brain Tumour Surgery
On the public ReMIND dataset, a systematic benchmark of six synthesis models across 48 experiments finds LPIPS correlates with downstream segmentation utility while SSIM does not, with SynDiff-2.5D performing best.
-
Heterogeneity-Adaptive Diffusion Schrodinger Bridge for PET-Guided Whole-Body MRI Translation
HA-DSB uses a diffusion Schrödinger bridge with vision-language model region embeddings and PET-guided noise modulation to translate whole-body MRI while preserving lesion fidelity.
-
Fully Guided Neural Schr\"odinger bridge for Brain MR image synthesis
FGSB is a two-stage neural Schrödinger bridge that generates missing MRI modalities from limited paired data and preserves lesions via expert priors.