Usefulness of synthetic datasets for diatom automatic detection using a deep-learning approach

Benthic diatoms are unicellular microalgae that are routinely used as bioindicators for monitoring the ecological status of freshwater. Their identification using light microscopy is a time-consuming and labor-intensive task that could be automated using deep-learning. However, training such networks relies on the availability of labeled datasets, which are difficult to obtain for these organisms. Herein, we propose a method to generate synthetic microscopy images for training. We gathered individual objects, i.e. 9230 diatoms from publicly available taxonomic guides and 600 items of debris from available real images. We collated a comprehensive dataset of synthetic microscopy images including both diatoms and debris using seamless blending and a combination of parameters such as image scaling, rotation, overlap and diatom-debris ratio. We then performed sensitivity analysis of the impact of the synthetic data parameters for training state-of-the art networks for horizontal and rotated bounding box detection (YOLOv5). We first trained the networks using the synthetic dataset and fine-tuned it to several real image datasets. Using this approach, the performance of the detection network was improved by up to 25% for precision and 23% for recall at an Intersection-over-Union(IoU) threshold of 0.5. This method will be extended in the future for training segmentation and classification networks.

Automated summary

In this study, a method of generating synthetic microscopy images for training algorithms using deep learning is proposed. A comprehensive dataset of synthetic microscopy images including diatoms and debris was collected using seamless blending and a combination of parameters. After training the networks using the synthetic dataset and fine-tuning them with real image datasets, the performance of the detection network was improved by up to 25% for precision and 23% for recall at an IoU threshold of 0.5. This method can be extended for training segmentation and classification networks in the future.