WinstonHuTiger/2D_VAE_UDA_for_3D_sythesis
Pytorch implementation of MICCAI-2022 paper, Domain-adaptive 3D Medical Image Synthesis: An Efficient Unsupervised Approach https://arxiv.org/pdf/2207.00844.pdf
This tool helps medical researchers and clinicians generate synthetic 3D medical images, like T1-weighted MRI scans, from other existing scans such as FLAIR and T2-weighted images. It takes a collection of medical image scans (e.g., MRIs from different sequences or modalities) as input and outputs high-quality, synthesized 3D images of a desired modality. This is especially useful for medical professionals needing to fill in missing scan data or prepare images for various downstream analysis tasks across different hospital datasets.
No commits in the last 6 months.
Use this if you need to generate high-quality 3D medical images from existing scans, especially when dealing with data from different sources or scanners that might have slight variations (domain shifts).
Not ideal if you are looking for a tool to analyze or segment medical images directly without needing to synthesize new ones first.
Stars
21
Forks
3
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Jul 05, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/WinstonHuTiger/2D_VAE_UDA_for_3D_sythesis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MASILab/SynBOLD-DisCo
Synthetic BOLD images for distortion correction of fMRI without additional calibration scans
BioMedAI-UCSC/InverseSR
[Early Accepted at MICCAI 2023] Pytorch Code of "InverseSR: 3D Brain MRI Super-Resolution Using...
NVlabs/SMRD
SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models
Yebulabula/DisC-Diff
【MICCAI 2023, Early accept】DisC-Diff: Disentangled Conditional Diffusion Model for...
ctom2/lucyd-deconvolution
[MICCAI 2023] This is the official code for the paper "A Feature-Driven Richardson-Lucy...