jwmao1/MedSegFactory

[ICCV 2025] MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs

39
/ 100
Emerging

This tool helps medical researchers and practitioners generate high-quality pairs of medical images and their corresponding segmentation masks. You provide a text description specifying the imaging modality, anatomical region, and conditions (e.g., 'breast ultrasound showing a tumor'), and it produces a synthetic medical image alongside an accurate mask highlighting the specified features. It's ideal for scientists and clinicians working on medical image analysis, machine learning model training, or research that requires diverse and high-volume medical imaging data.

Use this if you need to quickly create realistic medical image-mask pairs for training AI models, conducting research, or overcoming data scarcity in medical imaging, without dealing with patient data or time-consuming manual annotation.

Not ideal if you require real patient data for clinical diagnosis or if your primary need is general image generation outside of medical imaging applications.

medical imaging radiology research clinical data synthesis medical AI training biomedical research
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

32

Forks

2

Language

Python

License

MIT

Last pushed

Jan 26, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/jwmao1/MedSegFactory"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.