LucaLumetti/UNetTransplant
Repository for the paper "U-Net Transplant: The Role of Pre-training for Model Merging in 3D Medical Segmentation" accepted @ MICCAI2025
This project helps medical imaging specialists combine multiple specialized AI segmentation models into a single, comprehensive model without needing to retrain everything from scratch. You input several trained models, each skilled at segmenting a specific anatomical structure in 3D medical scans, and it outputs a merged model capable of segmenting all those structures. This is ideal for radiologists, clinicians, or researchers working with diverse 3D medical image analysis tasks who need efficient model updates.
No commits in the last 6 months.
Use this if you have multiple AI models, each trained for a specific 3D medical segmentation task (e.g., segmenting kidneys, then another for the liver) and you want to efficiently merge them into one model to handle all tasks simultaneously.
Not ideal if you are looking for a tool to train a segmentation model from scratch or if you only need a single, isolated segmentation task without merging capabilities.
Stars
31
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LucaLumetti/UNetTransplant"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
BiaPyX/BiaPy
Open source Python library for building bioimage analysis pipelines
Abe404/root_painter
RootPainter: Deep Learning Segmentation of Biological Images with Corrective Annotation
junlabucsd/napari-mm3
Mother machine image analysis through napari
Dootmaan/MT-UNet
Official Code for *Mixed Transformer UNet for Medical Image Segmentation*
chanzuckerberg/napari-hub
Discover, install, and share napari plugins