
by German Cancer Research Center
nnU-Net is an open-source segmentation framework that analyzes a dataset and configures its own U-Net pipeline, from preprocessing to training and inference. It is mainly used for biomedical image segmentation.
Web appFree
Step 1: Install PyTorch for your hardware.
Step 2: Run pip install nnunetv2.
Step 3: Set up the nnUNet_raw, nnUNet_preprocessed and nnUNet_results folders.
Step 4: Prepare your dataset following the dataset preparation guide.
Step 5: Train models, then run inference with the trained model.
It is built for supervised semantic segmentation, primarily of biomedical images, in 2D and 3D.
No. The cascade, for example, is only generated when the dataset characteristics justify it.
This is version 2, a complete reimplementation of the original. Version 1 lives on a separate branch and there is a migration guide.
Cite the 2021 Nature Methods paper by Isensee and colleagues, as the readme requests.
Azure Health BotAzure Health Bot applies AI to cloud platform for building healthcare conversational AI experiences with clinical content and configurable care workflows.
BiomedCLIPBiomedCLIP is a biomedical vision-language model from Microsoft, pretrained on 15 million figure-caption pairs from PubMed Central. It supports retrieval, image classification and visual question answering research.