Python backend for nnInteractive: Redefining 3D Promptable Segmentation
This repository provides the official Python backend for nnInteractive, a state-of-the-art framework for 3D promptable segmentation. It is designed for seamless integration into Python-based workflows—ideal for researchers, developers, and power users working directly with code.
nnInteractive is also available through graphical viewers (GUI) for those who prefer a visual workflow.
Recommended integrations (developed and maintained by our team)
Community-driven integrations
Huge thanks to the community for contributing these integrations!
📰 News
- 06/2026: 🐳 The inference server now ships as a Docker image — run nnInteractive on a GPU box with a single
docker run, no install required. See DOCKER.md
- 05/2026: 🌐 Remote GPU inference (client/server): drive nnInteractive over HTTP from a machine without a GPU via
nnInteractiveRemoteInferenceSession, with one server hosting multiple concurrent sessions. See SERVER_CLIENT.md
- 11/2025: 🌐 New community driven OHIF integration released by our colleagues at CCI Bonn. Try nnInteractive directly in OHIF 👉 OHIF-AI
- 07/2025: 🧩 New ITK-SNAP extension released! Try nnInteractive directly in ITK-SNAP 👉 Quick Start
- 06/2025: 🏆 We’re thrilled to announce that
nnInteractive won the 1st place in the CVPR 2025 Challenge on Interactive 3D Segmentation. Huge shoutout to the organizers and all contributors!
- 05/2025:
nnInteractive presents an official baseline at CVPR 2025 in the Foundation Models for Interactive 3D Biomedical Image Segmentation Challenge (Codabench link) → see nnInteractive/inference/cvpr2025_challenge_baseline
- 04/2025: 🎉 The community contributed a 3D Slicer integration – thank you! 👉 SlicerNNInteractive
- 03/2025: 🚀
nnInteractive launched with native support for napari and MITK
What is nnInteractive?
Isensee, F.*, Rokuss, M.*, Krämer, L.*, Dinkelacker, S., Ravindran, A., Stritzke, F., Hamm, B., Wald, T., Langenberg, M., Ulrich, C., Deissler, J., Floca, R., & Maier-Hein, K. (2025). nnInteractive: Redefining 3D Promptable Segmentation. https://arxiv.org/abs/2503.08373
*: equal contribution
Link:
Abstract:
Accurate and efficient 3D segmentation is essential for both clinical and research applications. While foundation
models like SAM have revolutionized interactive segmentation, their 2D design and domain shift limitations make them
ill-suited for 3D medical images. Current adaptations address some of these challenges but remain limited, either
lacking volumetric awareness, offering restricted interactivity, or supporting only a small set of structures and
modalities. Usability also remains a challenge, as current tools are rarely integrated into established imaging
platforms and often rely on cumbersome web-based interfaces with restricted functionality. We introduce nnInteractive,
the first comprehensive 3D interactive open-set segmentation method. It supports diverse prompts—including points,
scribbles, boxes, and a novel lasso prompt—while leveraging intuitive 2D interactions to generate full 3D
segmentations. Trained on 120+ diverse volumetric 3D datasets (CT, MRI, PET, 3D Microscopy, etc.), nnInteractive
sets a new state-of-the-art in accuracy, adaptability, and usability. Crucially, it is the first method integrated
into widely used image viewers (e.g., Napari, MITK), ensuring broad accessibility for real-world clinical and research
applications. Extensive benchmarking demonstrates that nnInteractive far surpasses existing methods, setting a new
standard for AI-driven interactive 3D segmentation.
Installation
nnInteractive ships as two pip packages — install only what you need:
nninteractive-client — lightweight remote client that drives a remote
nninteractive-server (via nnInteractiveRemoteInferenceSession). No PyTorch, no GPU —
only numpy / httpx / blosc2. Ideal for a GUI or thin client.nnInteractive — the full stack: the local inference engine and the official
server. Needs PyTorch and an NVIDIA GPU (10 GB VRAM recommended; small objects work with
<6 GB). It depends on nninteractive-client, so it includes the remote client too.
Both expose the same nnInteractive import namespace, so client code is identical either way.
This is the beginning of the README. Read the rest at the original. Read the full README ↗
