Towards a Digital Diatom: image processing and deep learning analysis of Bacillaria paradoxa dynamic morphology

Abstract

Recent years have witnessed a convergence of data and methods that allow us to approximate the shape, size, and functional attributes of biological organisms. This is not only limited to traditional model species: given the ability to culture and visualize a specific organism, we can capture both its structural and functional attributes. We present a quantitative model for the colonial diatom Bacillaria paradoxa, an organism that presents a number of unique attributes in terms of form and function. To acquire a digital model of B. paradoxa, we extract a series of quantitative parameters from microscopy videos from both primary and secondary sources. These data are then analyzed using a variety of techniques, including two rival deep learning approaches. We provide an overview of neural networks for non-specialists as well as present a series of analysis on Bacillaria phenotype data. The application of deep learning networks allows for two analytical purposes. Application of the DeepLabv3 pre-trained model extracts phenotypic parameters describing the shape of cells constituting Bacillaria colonies. Application of a semantic model trained on nematode embryogenesis data (OpenDevoCell) provides a means to analyze masked images of potential intracellular features. We also advance the analysis of Bacillaria colony movement dynamics by using templating techniques and biomechanical analysis to better understand the movement of individual cells relative to an entire colony. The broader implications of these results are presented, with an eye towards future applications to both hypothesis-driven studies and theoretical advancements in understanding the dynamic morphology of Bacillaria.

Plant phenotyping relevance

珪藻の顕微鏡動画から形態・細胞内特徴・群体運動を抽出する画像処理および深層学習手法が研究の中心であり、植物表現型解析手法の開発に該当する。

Code and data availability

The paper's Bacillaria phenotyping data and analysis assets are publicly available: raw data, processed numeric/image data, and code in the authors' Digital-Bacillaria GitHub repository; skeleton-creation scripts in the Image-Skeletons subrepository; the OpenDevoCell segmentation platform (GitHub and web app); and a Gf