nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation
arXiv:1809.10486
Abstract
The U-Net was presented in 2015. With its straight-forward and successful architecture it quickly evolved to a commonly used benchmark in medical image segmentation. The adaptation of the U-Net to novel problems, however, comprises several degrees of freedom regarding the exact architecture, preprocessing, training and inference. These choices are not independent of each other and substantially impact the overall performance. The present paper introduces the nnU-Net ('no-new-Net'), which refers to a robust and self-adapting framework on the basis of 2D and 3D vanilla U-Nets. We argue the strong case for taking away superfluous bells and whistles of many proposed network designs and instead focus on the remaining aspects that make out the performance and generalizability of a method. We evaluate the nnU-Net in the context of the Medical Segmentation Decathlon challenge, which measures segmentation performance in ten disciplines comprising distinct entities, image modalities, image geometries and dataset sizes, with no manual adjustments between datasets allowed. At the time of manuscript submission, nnU-Net achieves the highest mean dice scores across all classes and seven phase 1 tasks (except class 1 in BrainTumour) in the online leaderboard of the challenge.
References in corpus (2)
Cited by in corpus (73)
- CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation
- Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem
- Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation
- Modality specific U-Net variants for biomedical image segmentation: A survey
- Multi-Scale Supervised 3D U-Net for Kidneys and Kidney Tumor Segmentation
- Reinventing 2D Convolutions for 3D Images
- Multi-scale fully convolutional neural networks for histopathology image segmentation: from nuclear aberrations to the global tissue architecture
- Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection
- Scalable Neural Architecture Search for 3D Medical Image Segmentation
- Interactive segmentation of medical images through fully convolutional neural networks
- A persistent homology-based topological loss for CNN-based multi-class segmentation of CMR
- Known Operator Learning and Hybrid Machine Learning in Medical Imaging -- A Review of the Past, the Present, and the Future
- Robust Medical Instrument Segmentation Challenge 2019
- MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers
- U-Net Using Stacked Dilated Convolutions for Medical Image Segmentation
- GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentation
- MONAIfbs: MONAI-based fetal brain MRI deep learning segmentation
- M3d-CAM: A PyTorch library to generate 3D data attention maps for medical deep learning
- Conquering Data Variations in Resolution: A Slice-Aware Multi-Branch Decoder Network
- Efficient, high-performance pancreatic segmentation using multi-scale feature extraction
- C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation
- Domain specific cues improve robustness of deep learning based segmentation of ct volumes
- DefectNET: multi-class fault detection on highly-imbalanced datasets
- Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation
- Cell Segmentation by Combining Marker-Controlled Watershed and Deep Learning
- Axial multi-layer perceptron architecture for automatic segmentation of choroid plexus in multiple sclerosis
- End-to-End Adversarial Shape Learning for Abdomen Organ Deep Segmentation
- Deep learning in magnetic resonance prostate segmentation: A review and a new perspective
- Myocardial Segmentation of Cardiac MRI Sequences with Temporal Consistency for Coronary Artery Disease Diagnosis
- Hepatic vessel segmentation based on 3D swin-transformer with inductive biased multi-head self-attention
- Self-Adaptive 2D-3D Ensemble of Fully Convolutional Networks for Medical Image Segmentation
- Positional Contrastive Learning for Volumetric Medical Image Segmentation
- LAMP: Large Deep Nets with Automated Model Parallelism for Image Segmentation
- More than Encoder: Introducing Transformer Decoder to Upsample
- Marginal loss and exclusion loss for partially supervised multi-organ segmentation
- Robust Pancreatic Ductal Adenocarcinoma Segmentation with Multi-Institutional Multi-Phase Partially-Annotated CT Scans
- Pre-examinations Improve Automated Metastases Detection on Cranial MRI
- Learning Shape Priors by Pairwise Comparison for Robust Semantic Segmentation
- Self-Training Based Unsupervised Cross-Modality Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation
- Resource Optimized Neural Architecture Search for 3D Medical Image Segmentation
- DLBC: A Deep Learning-Based Consensus in Blockchains for Deep Learning Services
- ImageTBAD: A 3D Computed Tomography Angiography Image Dataset for Automatic Segmentation of Type-B Aortic Dissection
- Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss
- Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation
- Causality-inspired Single-source Domain Generalization for Medical Image Segmentation
- Transformer for Polyp Detection
- Uncertainty-aware Incremental Learning for Multi-organ Segmentation
- Brain tumour segmentation using cascaded 3D densely-connected U-net
- Ensembled ResUnet for Anatomical Brain Barriers Segmentation
- Automatic CT Segmentation from Bounding Box Annotations using Convolutional Neural Networks
- Towards Cardiac Intervention Assistance: Hardware-aware Neural Architecture Exploration for Real-Time 3D Cardiac Cine MRI Segmentation
- Estimating MRI Image Quality via Image Reconstruction Uncertainty
- Sli2Vol: Annotate a 3D Volume from a Single Slice with Self-Supervised Learning
- Contrastive Learning with Temporal Correlated Medical Images: A Case Study using Lung Segmentation in Chest X-Rays
- 3D medical image segmentation with labeled and unlabeled data using autoencoders at the example of liver segmentation in CT images
- Training CNN Classifiers for Semantic Segmentation using Partially Annotated Images: with Application on Human Thigh and Calf MRI
- Comparing Deep Learning strategies for paired but unregistered multimodal segmentation of the liver in T1 and T2-weighted MRI
- UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation
- Enabling Data Diversity: Efficient Automatic Augmentation via Regularized Adversarial Training
- Learning Non-Unique Segmentation with Reward-Penalty Dice Loss
- Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems
- Lesion Segmentation and RECIST Diameter Prediction via Click-driven Attention and Dual-path Connection
- DeepPrognosis: Preoperative Prediction of Pancreatic Cancer Survival and Surgical Margin via Contrast-Enhanced CT Imaging
- Segmentation with Multiple Acceptable Annotations: A Case Study of Myocardial Segmentation in Contrast Echocardiography
- Hepatocellular Carcinoma Segmentation from Digital Subtraction Angiography Videos using Learnable Temporal Difference
- Neuro4Neuro: A neural network approach for neural tract segmentation using large-scale population-based diffusion imaging
- Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation
- Automated Segmentation of Brain Gray Matter Nuclei on Quantitative Susceptibility Mapping Using Deep Convolutional Neural Network
- Survival-oriented embeddings for improving accessibility to complex data structures
- 3D Graph Anatomy Geometry-Integrated Network for Pancreatic Mass Segmentation, Diagnosis, and Quantitative Patient Management
- Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation
- Evidential segmentation of 3D PET/CT images
- PGD-UNet: A Position-Guided Deformable Network for Simultaneous Segmentation of Organs and Tumors