MIC-DKFZ ORG

No description.

nnU-Net is a Python framework that automatically configures and trains AI models to label regions in medical images like tumors or organs, removing the need for manual architecture tuning.

The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.

A framework for data augmentation for 2D and 3D image classification and segmentation

nnDetection is a self-configuring framework for 3D (volumetric) medical object detection which can be applied to new data sets without manual intervention. It includes guides for 12 data sets that were used to develop and evaluate the performance of the proposed method.

[MICCAI 2023] MedNeXt is a fully ConvNeXt architecture for 3D medical image segmentation.

MRI brain extraction tool

nnInteractive is a framework for 3D interactive segmentation, supporting intuitive prompts like points, scribbles, bounding boxes, and lasso. Trained on 120+ diverse 3D datasets, it sets a new standard in accuracy, usability, and adaptability for clinical and research applications.

Automatic White Matter Bundle Segmentation

Segment anything with our Napari integration of Meta AI's Segment Anything Model (SAM)!

Manage your machine learning experiments with trixi - modular, reproducible, high fashion. An experiment infrastructure optimized for PyTorch, but flexible enough to work for your framework and your tastes.

Free-Text Promptable Universal 3D Medical Image Segmentation

No description.

No description.

An example project of how to use a U-Net for segmentation on medical images with PyTorch.

Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures

nnInteractive plugin for Napari - nnInteractive is a framework for 3D interactive segmentation, supporting intuitive prompts like points, scribbles, bounding boxes, and lasso. Trained on 120+ diverse 3D datasets, it sets a new standard in accuracy, usability, and adaptability for clinical and research applications.

LesionLocator is a framework for zero-shot lesion segmentation and longitudinal tumor tracking in 3D full-body imaging.

MITK Diffusion - Official part of the Medical Imaging Interaction Toolkit

Scripts for the preprocessing of LIDC-IDRI data

No description.

This is a tool to quickly preview nifti images on the terminal

No description.

Implemention of the Paper "MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation"

Deep Learning Framework for Image Classification & Regression in Pytorch for Fast Experiments

Repository for the Medical Out-of-Distribution Analysis Challenge.

No description.

This repository holds the code framework used in the paper Reg R-CNN: Lesion Detection and Grading under Noisy Labels. It is a fork of MIC-DKFZ/medicaldetectiontoolkit with regression capabilites.

No description.

No description.

No description.

Swiss army knife for radiotherapy analysis

No description.

A grid sampler for larger-than-memory N-dimensional images

No description.

Code for deep learning-based glioma/tumor growth models

No description.

Hyppopy is a python toolbox for blackbox optimization. It's purpose is to offer a unified and easy to use interface to a collection of solver libraries.

A modular and extensible framework for training and evaluating semantic segmentation models with PyTorch Lightning, supporting multiple architectures, datasets, losses, and data augmentation pipelines out of the box.

No description.

No description.

No description.

A U-Net combined with a variational auto-encoder that is able to learn conditional distributions over semantic segmentations.

Array format specialized for Machine Learning with Blosc2 backend and standardized metadata.

No description.

nnActive -- code, benchmark and results for the largest study of Active Learning for 3D Biomedical Imaging.

No description.

Python wrapper to unify reading/writing via NiBabel, pynrrd and SimpleITK within a unified and simple interface.

No description.

Data Inspection Plugin, designed to streamline file navigation and enhance the efficiency of data inspection.

RadTract: enhanced tractometry with radiomics-based imaging biomarkers for improved predictive modelling.

No description.

Winning Solution of the ODELIA Breast MRI Challenge 2025

No description.

Longitudinal Segmentation of MS Lesions via Temporal Difference Weighting

This is a joint project between Helmholtz Imaging (located at DKFZ) and Lin Yang and Otmar Schmid (Helmholtz Munich).

No description.

No description.

No description.

No description.

The Radiomics Processing Toolkit (RPTK) is an automated self-optimizing Framework which can be used as a task-agnostic pipeline to predict radiomics-based biomarkers for any binary classification problem.

No description.

No description.

No description.

Automated Gleason Grading on WSI

Segment Anything model wrapper used by the Medical Imaging Interaction Toolkit (MITK).

An extension of YOLOv5 to non-natural images together with 5-Fold Cross-Validation

Prostate U-net

CmdInterface enables detailed logging of command line and python experiments in a very lightweight manner (coding wise). It wraps your command line or python function calls in a few lines of python code and logs everything you might need to reproduce the experiment later on or to simply check what you did a couple of years ago.

No description.

Code for "GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data"

No description.

No description.

MatchPoint is a translational image registration framework written in C++. It offers a standardized interface to utilize several registration algorithm resources (like ITK, plastimatch, elastix) easily in a host application.

No description.

[MICCAI 2025] Revisiting 3D Medical Scribble Supervision: Benchmarking Beyond Cardiac Segmentation

"Automated detection of aortic dissections (AD) from CT scans using deep segmentation and optimized thresholding. Applicable in emergency clinical settings, for research purposes only."

No description.

A lightweight napari toolkit for building plugins with Qt/QWidgets - enhanced widgets, reusable UI components, and utilities for cleaner layouts and smoother user interaction.

No description.

No description.

A unified Python toolkit for managing, processing, and analyzing 2D and 3D vision data — from raw files to task-aware analytics. Designed to streamline computer vision and medical imaging workflows and data pipelines.

No description.

No description.

No description.

No description.

A simple visualization tool for breast cancer classification

No description.

Multiprocessing with tqdm progressbars!

No description.

No description.

No description.

Code for the paper "Enhancing predictive imaging biomarker discovery through treatment effect analysis", which can be used for training and evaluating CATE estimation models for identifying predictive imaging biomarkers from pre-treatment images.

No description.

No description.

No description.

Plugin to send and receive multi-dimensional image data for visualization in Napari over the network.

A consensus radiomics workflow definition (proposal) initiated bei the SPP 2177 Radiomics

No description.

No description.

No description.

No description.

No description.

No description.

A reader/writer Napari plugin for MLArray images

No description.

Compact layer inspector for napari: fast statistics, editable geometry/camera fields, and clipboard-friendly summaries in one widget.

No description.

A plugin for flexible and intuitive color management of label layers in Napari, designed to enhance the visual clarity and control of your labeled data. Assign custom colors to individual classes using a color picker or RGB input, adjust per-class opacity, and apply colormaps to visually distinguish between labels with ease.

A Napari plugin that provides control over camera settings and allows saving and loading full viewer configurations to easily recreate and share consistent visual perspectives.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

This repository provides Docker images for running nnUNet inference in a reproducible and containerized environment, tailored for the EUCAIM project.

No description.

Automated processing of Versatile Image Data.

No description.

No description.

No description.

No description.