Synthetic Image Rendering Solves Annotation Problem in Deep Learning Nanoparticle Segmentation. Issue 7 (3rd May 2021)

• Record Type: Journal Article
• Authors: Mill, Leonid; Wolff, David; Gerrits, Nele; Philipp, Patrick; Kling, Lasse; Vollnhals, Florian; Ignatenko, Andrew; Jaremenko, Christian; Huang, Yixing; De Castro, Olivier; Audinot, Jean‐Nicolas; Nelissen, Inge; Wirtz, Tom; Maier, Andreas; Christiansen, Silke
• Is Part Of: Small methods. Volume 5:Issue 7(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-05-03
• Subjects: helium ion microscopy -- image analysis -- machine learning -- nanoparticles -- segmentation -- toxicology; Nanotechnology -- Methodology -- Periodicals; Nanotechnology -- Periodicals; Periodicals; 620.5028
• DOI: 10.1002/smtd.202100223
• Languages: English
• ISSNs: 2366-9608

Abstract

Abstract: 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. Abstract : In this study, a state‐of‐the art deep learning approach is introduced for the segmentation of complex nanoparticle agglomerates in helium ion microscopy images without the need for real training data. The proposed methodology paves the way toward automated and high‐throughput nanoparticle image analysis for a variety of applications.