nnFoundation: 3D Foundation Models for Radiology

arXiv:2609.26924 · cs.CV, eess.IV · Submitted 2026-09-22 · Read on arXiv

cs.CV, eess.IV

Submitted: 2026-09-22

Updated: 2026-09-22

Code: https://github.com/MIC-DKFZ/BodyPartRegression

Terminology

• nnU-Net — 112× in this paper · explained in 2 episodes
• Foundation Model — 62× in this paper · explained in 3 episodes
• Foundation Models — 49× in this paper · explained in 7 episodes
• Benchmark — 45× in this paper · explained in 2 episodes
• Fine-Tuning — 44× in this paper · explained in 5 episodes
• Core — 39× in this paper · explained in 2 episodes
• Adaptation — 32× in this paper · explained in 1 episode
• AUROC — 28× in this paper · explained in 2 episodes
• Transformer — 28× in this paper · explained in 2 episodes
• Robustness — 18× in this paper · explained in 5 episodes
• External Validation — 14× in this paper · explained in 2 episodes
• Generalization — 14× in this paper · explained in 13 episodes
• Domain Shift — 9× in this paper · explained in 4 episodes
• Downstream Tasks — 9× in this paper · explained in 2 episodes
• Alignment — 8× in this paper · explained in 1 episode
• Contrastive Learning — 8× in this paper · explained in 5 episodes
• Institute Clinical Proteomic Tumor Analysis Consortium — 8× in this paper
• Self-Supervised Learning — 7× in this paper · explained in 8 episodes
• Anisotropy — 6× in this paper · explained in 3 episodes
• Distribution Shift — 6× in this paper · explained in 6 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Benchmarking — 4× in this paper · explained in 3 episodes
• Laboratory of Neuro Imaging — 4× in this paper
• Representation Learning — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Aggregation — 3× in this paper · explained in 1 episode
• Dynamic Adaptation — 3× in this paper · explained in 2 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Medical Segmentation Decathlon — 3× in this paper
• Segmentation Masks — 3× in this paper · explained in 2 episodes
• Semantic Understanding — 3× in this paper · explained in 2 episodes
• Transferability — 3× in this paper · explained in 4 episodes
• Cancer Imaging Archive — 2× in this paper
• Generalizability — 2× in this paper · explained in 6 episodes
• Helmholtz Metadata Collaboration — 2× in this paper
• Lung Image Database Consortium — 2× in this paper
• Medical Imaging Data Resource Center — 2× in this paper
• Transformer Architecture — 2× in this paper · explained in 2 episodes
• Vision-language models — 2× in this paper · explained in 2 episodes
• Active Learning — 1× in this paper · explained in 6 episodes
• Adaptive Planning — 1× in this paper · explained in 1 episode
• Adolescent Brain Cognitive Development — 1× in this paper
• Artificial Intelligence (AI) — 1× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Convolutional Neural Network — 1× in this paper
• Distillation — 1× in this paper · explained in 2 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Federated Learning — 1× in this paper · explained in 15 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Hybrid Architectures — 1× in this paper · explained in 3 episodes
• Instance Segmentation — 1× in this paper · explained in 3 episodes
• International Consortium for Brain Mapping — 1× in this paper
• Longitudinal Evaluation of Amyloid Risk and Neurodegeneration — 1× in this paper
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• Modality Gap — 1× in this paper · explained in 4 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• National Center for Tumor Diseases — 1× in this paper
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Pseudo-labeling — 1× in this paper · explained in 3 episodes
• Self-Distillation — 1× in this paper · explained in 7 episodes
• Semi-supervised Learning — 1× in this paper · explained in 4 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Standardized Benchmarks — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• DINOv3
• BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs
• AMAES: Augmented Masked Autoencoder Pretraining on Public Brain MRI Data for 3D-Native Segmentation
• MIS-FM: 3D Medical Image Segmentation using Foundation Models Pretrained on a Large-Scale Unannotated Dataset
• Vision Foundation Models for Computed Tomography
• Primus: Enforcing Attention Usage for 3D Medical Image Segmentation
• Advancing Volumetric Medical Image Segmentation via Global-Local Masked Autoencoder
• HySparK: Hybrid Sparse Masking for Large Scale Medical Image Pre-Training
• MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling
• SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluation
• The Brain Tumor Segmentation in Pediatrics (BraTS-PEDs) Challenge: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs)
• The 2024 Brain Tumor Segmentation (BraTS) Challenge: Glioma Segmentation on Post-treatment MRI
• A European Multi-Center Breast Cancer MRI Dataset
• The KiTS21 Challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CT
• The Brain Tumor Segmentation (BraTS-METS) Challenge 2023: Brain Metastasis Segmentation on Pre-treatment MRI
• STU-Net: Scalable and Transferable Medical Image Segmentation Models Empowered by Large-Scale Supervised Pre-training
• Curia: A Multi-Modal Foundation Model for Radiology
• Learning neuroimaging models from health system-scale data
• MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imaging
• OmniRad: A Radiological Foundation Model for Multi-Task Medical Image Analysis

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models