Segmentation priors from Swin UNETR condition CycleGAN and transformer residual models whose weighted outputs synthesize 3 T-like MRIs from 64 mT scans, reported as comparable to high-field images in the ULF Enhancement Challenge.
arXiv preprint arXiv:2402.17317 (2024)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
citing papers explorer
-
Enhancing Ultra-low-field MRI with Segmentation-guided Adversarial Learning
Segmentation priors from Swin UNETR condition CycleGAN and transformer residual models whose weighted outputs synthesize 3 T-like MRIs from 64 mT scans, reported as comparable to high-field images in the ULF Enhancement Challenge.