Synthetic Image Rendering Solves Annotation Problem in Deep Learning Nanoparticle Segmentation
Creators
- 1. Pattern Recognition Lab Friedrich-Alexander-University Erlangen-Nuremberg 91058 Erlangen, Germany
- 2. Institut für Nanotechnologie und korrelative Mikroskopie 91301 Forchheim, Germany
- 3. Health Unit Flemish Institute for Technological Research Mol 2400, Belgium
- 4. Advanced Instrumentation for Nano-Analytics (AINA), MRT Department, Luxembourg Institute of Science and Technology, 41 rue du Brill, L-4422 Belvaux, Luxembourg
- 5. Institute of Optics, Information and Photonics Friedrich-Alexander-University Erlangen-Nuremberg 91058 Erlangen, Germany
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, highthroughput 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.
Notes
Files
Small Methods 5 2021 2100223 Mill.pdf
Files
(2.7 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:ebd648f92a1fdcd363b984dafbdab8a8
|
2.7 MB | Preview Download |
Additional details
Funding
- 4-D nanoSCOPE – Advancing osteoporosis medicine by observing bone microstructure and remodelling using a four-dimensional nanoscope 810316
- European Commission
- npSCOPE – The nanoparticle-scope : a new integrated instrument for accurate and reproducible physico-chemical characterisation of nanoparticles (npSCOPE) 720964
- European Commission