# mic-dkfz/nnunet **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/mic-dkfz-nnunet).** 8,041 stars · 2,301 forks · Python · apache-2.0 ## Links - GitHub: https://github.com/MIC-DKFZ/nnUNet - awesome-repositories: https://awesome-repositories.com/repository/mic-dkfz-nnunet.md ## Topics `segmentation` ## Description nnU-Net is a PyTorch-based deep learning framework for the supervised semantic segmentation of 2D and 3D biomedical images. It functions as an automated medical imaging pipeline that generates predicted masks and labels from clinical images. The system distinguishes itself by using dataset-driven auto-configuration to automatically select the optimal network architecture, preprocessing steps, and training hyperparameters based on the specific properties of the input medical dataset. The framework covers a broad range of capabilities including medical dataset preparation, intensity normalization, and supervised segmentation training. It incorporates specialized training features such as sparse annotation handling and region-based label optimization, alongside an inference engine that utilizes sliding-window execution. Evaluation tools are provided for benchmarking both hardware performance and model segmentation accuracy. ## Tags ### Artificial Intelligence & ML - [Segmentation Model Training](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/image-segmentation/segmentation-model-training.md) — Provides a comprehensive framework for preparing datasets and executing supervised training for biomedical image segmentation. ([source](https://github.com/MIC-DKFZ/nnUNet/tree/master/documentation/how-to)) - [Dataset-Driven Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/machine-learning-training/training-configuration-management/training-hyperparameter-configurations/dataset-driven-configurations.md) — Automatically selects the optimal network architecture and training hyperparameters based on the specific properties of the input medical dataset. - [Automated Architecture Selection](https://awesome-repositories.com/f/artificial-intelligence-ml/automated-architecture-selection.md) — Automatically adjusts network architectures and hyperparameters based on the specific properties of the image dataset. - [Automated Medical Imaging Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/automated-medical-imaging-pipelines.md) — Functions as an automated medical imaging pipeline that configures preprocessing and network architecture based on dataset properties. - [Image Segmentation](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/image-segmentation.md) — Trains deep learning models to automatically identify and outline anatomical structures in 2D and 3D medical images. - [Automated Configuration Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/image-segmentation/segmentation-model-training/segmentation-dataset-loaders/automated-configuration-pipelines.md) — Automatically selects the optimal network architecture and hyperparameters based on the specific properties of the medical dataset. ([source](https://cdn.jsdelivr.net/gh/mic-dkfz/nnunet@master/README.md)) - [Sparse Annotation Handling](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/image-segmentation/segmentation-model-training/sparse-annotation-handling.md) — Allows learning from datasets with incomplete manual segmentations by ignoring unlabeled regions during training. ([source](https://github.com/MIC-DKFZ/nnUNet/tree/master/documentation/explanation)) - [Patch-Based Training Strategies](https://awesome-repositories.com/f/artificial-intelligence-ml/image-convolution-operations/image-patch-embedders/tensor-patch-extraction/patch-based-training-strategies.md) — Processes large 3D volumes by extracting small overlapping sub-volumes to enable training within limited GPU memory. - [Inference Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/inference-execution.md) — Provides a process that applies trained segmentation models to new images to generate predicted masks and labels. ([source](https://github.com/MIC-DKFZ/nnUNet/tree/master/documentation/getting-started)) - [Supervised Learning Models](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/algorithms/core-algorithmic-paradigms/supervised-learning-models.md) — Implements a supervised learning system for generating predicted masks and labels from medical images. - [U-Net Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-architectures/u-net-architectures.md) — Utilizes a symmetric encoder-decoder U-Net structure with residual connections for multi-scale spatial feature capture. - [PyTorch Semantic Segmentation Libraries](https://awesome-repositories.com/f/artificial-intelligence-ml/pytorch-semantic-segmentation-libraries.md) — Provides a deep learning framework for semantic segmentation of 2D and 3D biomedical images using PyTorch. - [Dataset-Adaptive](https://awesome-repositories.com/f/artificial-intelligence-ml/training-pipelines/dataset-adaptive.md) — Adapts network architecture, preprocessing, and hyperparameters based on the specific properties of the provided biomedical dataset. ([source](https://github.com/MIC-DKFZ/nnUNet/tree/master/documentation/reference)) - [Cascaded Segmentation Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/cascaded-segmentation-pipelines.md) — Implements a cascaded model pipeline that sequentially applies coarse and fine networks to refine anatomical boundaries. - [Sparse Annotation Training](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/image-segmentation/segmentation-model-training/sparse-annotation-training.md) — Develops segmentation models using datasets with incomplete or coarse manual labels by ignoring unlabeled regions. - [Model Performance Benchmarking](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-evaluation-analysis/model-analysis/model-performance-benchmarking.md) — Ships an evaluation system for comparing model segmentation accuracy and processing speed using standardized datasets. ([source](https://github.com/MIC-DKFZ/nnUNet/tree/master/documentation/reference)) - [Anatomical Region Training](https://awesome-repositories.com/f/artificial-intelligence-ml/region-based-detection/anatomical-region-training.md) — Provides a training approach specifically designed to improve the segmentation of large anatomical structures. ([source](https://github.com/MIC-DKFZ/nnUNet/tree/master/documentation/how-to)) - [Anatomical Region Weighting](https://awesome-repositories.com/f/artificial-intelligence-ml/training-loop-schedulers/loss-weight-schedulers/anatomical-region-weighting.md) — Modifies the training objective to prioritize specific anatomical regions or ignore unlabeled areas in sparse datasets. - [Anatomical Region Weighting](https://awesome-repositories.com/f/artificial-intelligence-ml/training-optimization-techniques/anatomical-region-weighting.md) — Implements specialized loss functions that prioritize targeted anatomical areas to improve segmentation accuracy. ([source](https://github.com/MIC-DKFZ/nnUNet/tree/master/documentation/explanation)) ### Data & Databases - [Pixel Normalizers](https://awesome-repositories.com/f/data-databases/image-preprocessing-utilities/pixel-normalizers.md) — Provides utilities for scaling pixel intensity values using dataset-specific statistics to ensure consistent distributions across modalities. - [Medical Dataset Formatting](https://awesome-repositories.com/f/data-databases/medical-dataset-formatting.md) — Provides utilities for formatting raw medical images and labels into standardized structures for training. ([source](https://github.com/MIC-DKFZ/nnUNet/tree/master/documentation/how-to)) - [Medical Image Normalization](https://awesome-repositories.com/f/data-databases/medical-image-normalization.md) — Converts and normalizes raw medical imaging files into a standardized format for use in supervised learning pipelines. ### Education & Learning Resources - [Sliding-Window Inference](https://awesome-repositories.com/f/education-learning-resources/sliding-window-algorithms/sliding-window-inference.md) — Generates predictions by scanning the image with overlapping patches and averaging results to remove edge artifacts. ### Scientific & Mathematical Computing - [Segmentation Inference](https://awesome-repositories.com/f/scientific-mathematical-computing/applied-domain-sciences/medical-imaging-software/segmentation-inference.md) — Applies trained segmentation models to new clinical images to generate predicted masks and labels. - [Segmentation Inference Engines](https://awesome-repositories.com/f/scientific-mathematical-computing/applied-domain-sciences/medical-imaging-software/segmentation-inference-engines.md) — Implements a tool for applying trained deep learning models to new medical images to perform semantic segmentation. ### Graphics & Multimedia - [Biomedical Image Processing Toolkits](https://awesome-repositories.com/f/graphics-multimedia/biomedical-image-processing-toolkits.md) — Provides a set of tools for intensity normalization and dataset preparation of medical imaging formats.