Improving 3D deep learning segmentation with biophysically motivated cell synthesis
Abstract Biomedical research increasingly relies on three-dimensional (3D) cell culture models and artificial-intelligence-based analysis can potentially facilitate a detailed and accurate feature extraction on a single-cell level. However, this requires for a precise segmentation of 3D cell dataset...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Communications Biology |
| Online Access: | https://doi.org/10.1038/s42003-025-07469-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544359896416256 |
|---|---|
| author | Roman Bruch Mario Vitacolonna Elina Nürnberg Simeon Sauer Rüdiger Rudolf Markus Reischl |
| author_facet | Roman Bruch Mario Vitacolonna Elina Nürnberg Simeon Sauer Rüdiger Rudolf Markus Reischl |
| author_sort | Roman Bruch |
| collection | DOAJ |
| description | Abstract Biomedical research increasingly relies on three-dimensional (3D) cell culture models and artificial-intelligence-based analysis can potentially facilitate a detailed and accurate feature extraction on a single-cell level. However, this requires for a precise segmentation of 3D cell datasets, which in turn demands high-quality ground truth for training. Manual annotation, the gold standard for ground truth data, is too time-consuming and thus not feasible for the generation of large 3D training datasets. To address this, we present a framework for generating 3D training data, which integrates biophysical modeling for realistic cell shape and alignment. Our approach allows the in silico generation of coherent membrane and nuclei signals, that enable the training of segmentation models utilizing both channels for improved performance. Furthermore, we present a generative adversarial network (GAN) training scheme that generates not only image data but also matching labels. Quantitative evaluation shows superior performance of biophysical motivated synthetic training data, even outperforming manual annotation and pretrained models. This underscores the potential of incorporating biophysical modeling for enhancing synthetic training data quality. |
| format | Article |
| id | doaj-art-5fad8f72b4ab44c387554effb367c8c1 |
| institution | Kabale University |
| issn | 2399-3642 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Biology |
| spelling | doaj-art-5fad8f72b4ab44c387554effb367c8c12025-01-12T12:35:51ZengNature PortfolioCommunications Biology2399-36422025-01-018111310.1038/s42003-025-07469-2Improving 3D deep learning segmentation with biophysically motivated cell synthesisRoman Bruch0Mario Vitacolonna1Elina Nürnberg2Simeon Sauer3Rüdiger Rudolf4Markus Reischl5Institute for Automation and Applied Informatics, Karlsruhe Institute of TechnologyInstitute of Molecular and Cell Biology, Mannheim University of Applied SciencesInstitute of Molecular and Cell Biology, Mannheim University of Applied SciencesInstitute of Molecular and Cell Biology, Mannheim University of Applied SciencesInstitute of Molecular and Cell Biology, Mannheim University of Applied SciencesInstitute for Automation and Applied Informatics, Karlsruhe Institute of TechnologyAbstract Biomedical research increasingly relies on three-dimensional (3D) cell culture models and artificial-intelligence-based analysis can potentially facilitate a detailed and accurate feature extraction on a single-cell level. However, this requires for a precise segmentation of 3D cell datasets, which in turn demands high-quality ground truth for training. Manual annotation, the gold standard for ground truth data, is too time-consuming and thus not feasible for the generation of large 3D training datasets. To address this, we present a framework for generating 3D training data, which integrates biophysical modeling for realistic cell shape and alignment. Our approach allows the in silico generation of coherent membrane and nuclei signals, that enable the training of segmentation models utilizing both channels for improved performance. Furthermore, we present a generative adversarial network (GAN) training scheme that generates not only image data but also matching labels. Quantitative evaluation shows superior performance of biophysical motivated synthetic training data, even outperforming manual annotation and pretrained models. This underscores the potential of incorporating biophysical modeling for enhancing synthetic training data quality.https://doi.org/10.1038/s42003-025-07469-2 |
| spellingShingle | Roman Bruch Mario Vitacolonna Elina Nürnberg Simeon Sauer Rüdiger Rudolf Markus Reischl Improving 3D deep learning segmentation with biophysically motivated cell synthesis Communications Biology |
| title | Improving 3D deep learning segmentation with biophysically motivated cell synthesis |
| title_full | Improving 3D deep learning segmentation with biophysically motivated cell synthesis |
| title_fullStr | Improving 3D deep learning segmentation with biophysically motivated cell synthesis |
| title_full_unstemmed | Improving 3D deep learning segmentation with biophysically motivated cell synthesis |
| title_short | Improving 3D deep learning segmentation with biophysically motivated cell synthesis |
| title_sort | improving 3d deep learning segmentation with biophysically motivated cell synthesis |
| url | https://doi.org/10.1038/s42003-025-07469-2 |
| work_keys_str_mv | AT romanbruch improving3ddeeplearningsegmentationwithbiophysicallymotivatedcellsynthesis AT mariovitacolonna improving3ddeeplearningsegmentationwithbiophysicallymotivatedcellsynthesis AT elinanurnberg improving3ddeeplearningsegmentationwithbiophysicallymotivatedcellsynthesis AT simeonsauer improving3ddeeplearningsegmentationwithbiophysicallymotivatedcellsynthesis AT rudigerrudolf improving3ddeeplearningsegmentationwithbiophysicallymotivatedcellsynthesis AT markusreischl improving3ddeeplearningsegmentationwithbiophysicallymotivatedcellsynthesis |