jianqingzheng/def_diff_rec

[Medical Image Analysis] Deformation-Recovery Diffusion Model (DRDM): Instance Deformation for Image Manipulation and Synthesis

42
/ 100
Emerging

This tool helps medical researchers and practitioners generate diverse, realistic deformations of medical images, such as organ scans. You provide an original medical image, and it outputs multiple versions of that image with various non-rigid deformations, alongside corresponding deformation fields and labels. This is ideal for medical imaging scientists and clinicians involved in research or training using medical image data.

Use this if you need to create synthetic, diverse deformations of medical images to augment datasets for tasks like few-shot learning, image registration, or segmentation, especially when human annotation is scarce or impossible.

Not ideal if you are looking to register two distinct patient images to each other or if you need to perform rigid transformations without complex, non-linear organ movement.

medical-imaging radiology anatomical-modeling bioinformatics image-augmentation
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

29

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Feb 20, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/jianqingzheng/def_diff_rec"

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