Pith. sign in

REVIEW 13 cited by

nnInteractive: Redefining 3D Promptable Segmentation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.08373 v1 pith:6HRX5WFS submitted 2025-03-11 cs.CV

Fabian Isensee , Maximilian Rokuss , Lars Krämer , Stefan Dinkelacker , Ashis Ravindran , Florian Stritzke , Benjamin Hamm , Tassilo Wald
show 5 more authors
Moritz Langenberg Constantin Ulrich Jonathan Deissler Ralf Floca Klaus Maier-Hein
This is my paper
classification cs.CV
keywords nninteractivesegmentationhttpsinteractivemitkapplicationsclinicalcurrent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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. nnInteractive is publicly available: https://github.com/MIC-DKFZ/napari-nninteractive (Napari plugin), https://www.mitk.org/MITK-nnInteractive (MITK integration), https://github.com/MIC-DKFZ/nnInteractive (Python backend).

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MedSAM2-Anatomy: Training-Free Inference-Time Optimization for Musculoskeletal Segmentation

    eess.IV 2026-07 conditional novelty 6.0 of 10

    Routing a frozen expert's prior through a frozen promptable foundation model with multi-prompt fusion and a plausibility guard raises median Dice from 0.71 to 0.92 on hip MRI and 0.89 to 0.92 on shoulder CT, without a...

  2. Fast ungated five-dimensional cardiac MRI on a 1.5 T MR-linac for MRI-guided radiotherapy

    physics.med-ph 2026-07 conditional novelty 6.0 of 10

    One minute of ungated Cartesian MRI on an MR-linac can be reconstructed into separated cardiac and respiratory 5D motion states in six minutes using low-rank deformation fields.

  3. Universality Reconsidered: Rethinking the Validation of Foundation Models for General-Purpose 3D Medical Segmentation

    cs.CV 2026-02 conditional novelty 6.0 of 10

    Five 3D medical segmentation foundation models drop sharply on a new paired whole-body PET/CT and PET/MRI benchmark, especially on PET.

  4. Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation

    cs.CV 2025-12 conditional novelty 6.0 of 10

    An atlas-registration pipeline that prompts and fuses a frozen segmentation foundation model achieves one-shot customization, improving Dice on small and uncommon structures across six medical datasets.

  5. Live(r) Die: Predicting Survival in Colorectal Liver Metastasis

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A fully automated pre/post-contrast MRI framework, combining prompt-based segmentation with autoencoder multiple-instance survival analysis, improves CRLM post-surgery survival prediction over clinical and genomic bio...

  6. Self-Validated Learning for Particle Separation: A Correctness-Based Self-Training Framework Without Human Labels

    eess.IV 2025-08 unverdicted novelty 6.0 of 10

    A self-training method uses cross-scan particle matching instead of human labels to train and evaluate 3D particle instance segmentation, reporting 97 percent volume coverage and 54,000+ particles on quartz fragments.

  7. Divide and Conquer: A Large-Scale Dataset and Model for Left-Right Breast MRI Segmentation

    eess.IV 2025-07 conditional novelty 6.0 of 10

    The first large-scale public breast MRI dataset with explicit left and right breast segmentation labels, created via center-of-mass splitting and active learning, is released with a trained model.

  8. Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Rendering

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Render-FM predicts 6D Gaussian splatting parameters from a CT volume in a single feedforward pass, enabling real-time rendering with quality comparable to per-scan optimized methods.

  9. BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation

    cs.CV 2025-11 conditional novelty 5.0 of 10

    Splitting the background into anatomical sub-classes during training improves small-lesion segmentation in medical images across architectures and datasets.

  10. Promptable Longitudinal Lesion Segmentation in Whole-Body CT

    eess.IV 2025-08 conditional novelty 5.0 of 10

    Adding point and mask prompts to a longitudinal segmentation model, plus pretraining on synthetic CT pairs, improves whole-body lesion tracking Dice by up to 6 points.

  11. Towards Interactive Lesion Segmentation in Whole-Body PET/CT with Promptable Models

    cs.CV 2025-08 conditional novelty 5.0 of 10

    Adding click prompts encoded as Euclidean distance transforms to an nnU-Net improves interactive whole-body PET/CT lesion segmentation over Gaussian encodings and baseline autoPET III models.

  12. Effect of User-Prompted Priors on Semi-Automated Cancer Lesion Segmentation in Whole-Body Computed Tomography

    cs.CV 2026-07 conditional novelty 4.0 of 10

    Three-plane orthogonal contour priors lift nnU-Net whole-body CT lesion Dice to 0.882 versus 0.671 with no prior on 3865 external lesions.

  13. RAPS-3D: Efficient interactive segmentation for 3D radiological imaging

    cs.CV 2025-07 conditional novelty 4.0 of 10

    RAPS-3D is a 3D promptable CT segmentation model that reports 86.8 Dice on AMOS-CT with a single 2D bounding-box prompt, using zoom-out/zoom-in inference with no sliding window.

Pith tools