2026-08-01T00:50:41Z
https://rodare.hzdr.de/oai2d
oai:rodare.hzdr.de:4199
2026-01-07T15:21:39Z
software
user-health
user-hzdr
user-pet-center
user-rodare
user-zrt
true
3.1
HZDR.RODARE
10.14278/rodare.4199
Maus, Jens
0000-0002-7195-9927
Nitschke, Janina
Nikulin, Pavel
0000-0002-4568-4018
Hofheinz, Frank
0000-0001-8016-4643
Barth, Mareike
Lemm, Sandy
0000-0001-6763-5957
Richter, Lena
Pietzsch, Jens
0000-0002-1610-1493
Braune, Anja
0000-0001-7707-9413
Ullrich, Martin
0000-0001-6104-6676
pyMarAI: nnU-Net-based Tumor Spheroids Auto Delineation
Rodare
2026
Tumor Spheroid Imaging
Radiopharmacological Treatment Response Assays
Delineation
Cancer
Deep-Learning
Artifical Intelligence
Convolutional Neural Networks
Network model
2026-01-07
https://rodare.hzdr.de/record/4199
https://www.hzdr.de/publications/Publ-42498
https://www.hzdr.de/publications/Publ-42497
https://github.com/hzdr-MedImaging/pyMarAI
10.14278/rodare.4198
https://rodare.hzdr.de/communities/health
https://rodare.hzdr.de/communities/hzdr
https://rodare.hzdr.de/communities/pet-center
https://rodare.hzdr.de/communities/rodare
https://rodare.hzdr.de/communities/zrt
1.0.0
Creative Commons Attribution Share Alike 4.0 International
Open Access
<p>Collection of neural network models for automatic image segmentation of microscopic tumor spheroids. Intended to be used with nnU-Net deep-learning framework. Trained and tested on a total of microscopic images of mouse pheochromocytoma (MPC) tumor cells.</p>
<p>In addition to the trained network model, a PyQt5-based graphical user interface tool is provided. This tool provides a complete pipeline for handling microscopic spheroid image data, running deep-learning–based delineation, and curating results for continuous model improvement.</p>
<p>For installation and usage instructions, please visit <a href="https://github.com/hzdr-MedImaging/pyMarAI">https://github.com/hzdr-MedImaging/pyMarAI</a></p>
<p>Please cite <a href="https://www.nature.com/articles/s41592-020-01008-z">nnU-Net</a> and the respective paper when using pyMarAI.</p>
<p>List of available model types:</p>
<ul>
<li><code>pyMarAI-1.0.0-ecat.zip</code>: nnUNetv2 ready network (for ECAT7)</li>
<li><code>pyMarAI-1.0.0-nifti.zip</code>: nnUNetv2 ready network (for NIFTI)</li>
</ul>