|
Persistent Identifier
|
perma:LIST.FKJPNG |
|
Publication Date
|
2026-07-06 |
|
Title
| Synthetic Image Rendering Solves Annotation Problem in Deep Learning Nanoparticle Segmentation [* Cross-Reference *] |
|
Other Identifier
| https://doi.org/10.1002/smtd.202100223
SCOPUS_ID:85104930748 |
|
Author
| Mill, Leonid (Friedrich-Alexander-Universität Erlangen-Nürnberg, Friedrich-Alexander-Universität Erlangen-Nürnberg) - ORCID: 0000-0001-6449-7309
Wolff, David (Institut für Nanotechnologie und korrelative Mikroskopie)
Gerrits, Nele (Vlaamse Instelling voor Technologisch Onderzoek)
Philipp, Patrick (Luxembourg Institute of Science and Technology)
Kling, Lasse (Institut für Nanotechnologie und korrelative Mikroskopie)
Vollnhals, Florian (Friedrich-Alexander-Universität Erlangen-Nürnberg, Institut für Nanotechnologie und korrelative Mikroskopie)
Ignatenko, Andrew (Luxembourg Institute of Science and Technology)
Jaremenko, Christian (Friedrich-Alexander-Universität Erlangen-Nürnberg, Institut für Nanotechnologie und korrelative Mikroskopie)
Huang, Yixing (Friedrich-Alexander-Universität Erlangen-Nürnberg, Institut für Nanotechnologie und korrelative Mikroskopie)
De Castro, Olivier (Luxembourg Institute of Science and Technology)
Audinot, Jean Nicolas (Luxembourg Institute of Science and Technology)
Nelissen, Inge (Vlaamse Instelling voor Technologisch Onderzoek)
Wirtz, Tom (Luxembourg Institute of Science and Technology)
Maier, Andreas (Friedrich-Alexander-Universität Erlangen-Nürnberg)
Christiansen, Silke (Friedrich-Alexander-Universität Erlangen-Nürnberg, Freie Universität Berlin, Fraunhofer Institute for Ceramic Technologies and Systems IKTS) |
|
Point of Contact
|
Use email button above to contact.
LIST RDS (LIST) |
|
Description
| Nanoparticles occur in various environments as a consequence of man-made processes, which raises concerns about their impact on the environment and human health. To allow for proper risk assessment, a precise and statistically relevant analysis of particle characteristics (such as size, shape, and composition) is required that would greatly benefit from automated image analysis procedures. While deep learning shows impressive results in object detection tasks, its applicability is limited by the amount of representative, experimentally collected and manually annotated training data. Here, an elegant, flexible, and versatile method to bypass this costly and tedious data acquisition process is presented. It shows that using a rendering software allows to generate realistic, synthetic training data to train a state-of-the art deep neural network. Using this approach, a segmentation accuracy can be derived that is comparable to man-made annotations for toxicologically relevant metal-oxide nanoparticle ensembles which were chosen as examples. The presented study paves the way toward the use of deep learning for automated, high-throughput particle detection in a variety of imaging techniques such as in microscopies and spectroscopies, for a wide range of applications, including the detection of micro- and nanoplastic particles in water and tissue samples. (2021-07-01)
***This entry has been automatically imported via Infodoc(ASO) CSV by LIST harvest scripts. Please refer to https://doi.org/10.1002/smtd.202100223 for the original and latest version of the dataset and data downloads*** (2026-06-12) |
|
Subject
| Physics |
|
Keyword
| helium ion microscopy
image analysis
machine learning
nanoparticles
segmentation
toxicology |
|
Funding Information
| Horizon 2020 Framework Programme: 810316 |
|
Deposit Date
| 2021-07-01 |
|
Data Type
| Article |
|
Data Source
| Small Methods; eISSN: 23669608, vol. 5, n° 7, art. no. 2100223 |