LemuelPuglisi/BrLP

[MICCAI, 2024] (Oral, RU @ MedIA Best Paper Award) Official implementation of the Brain Latent Progression (BrLP) method from "Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledge"

43
/ 100
Emerging

Combines a variational autoencoder, diffusion-based UNet, and ControlNet architecture to model individual spatiotemporal brain disease progression from longitudinal 3D MRI scans in latent space. Integrates prior knowledge through auxiliary disease progression models (e.g., DCM) via ControlNet conditioning, enabling personalized trajectory prediction while reducing computational overhead. Provides a CLI tool with optional automatic brain segmentation via SynthSeg and inference through YAML configuration, built on MONAI's GenerativeModels framework.

122 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

122

Forks

9

Language

Python

License

MIT

Last pushed

Oct 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/LemuelPuglisi/BrLP"

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