Jessica Aceto

Automatic localization of interest points in zebrafish images with tree-based methods

In many biological studies, scientists assess effects of experimental conditions by visual inspection of microscopy images. They are able to observe whether a protein is expressed or not, if cells are going through normal cell cycles, how organisms evolve in different experimental conditions, etc. But, with the large number of images acquired in high-throughput experiments, this manual inspection becomes lengthy, tedious and error-prone. In this paper, we propose to automatically detect specific interest points in microscopy images using machine learning methods with the aim of performing automatic morphometric measurements in the context of Zebrafish studies. We systematically evaluate variants of ensembles of classification and regression trees on four datasets corresponding to different imaging modalities and experimental conditions. Our results show that all variants are effective, with a slight advantage for multiple output methods, which are more robust to parameter choices.

Effects of microgravity simulation on zebrafish transcriptomes and bone physiology—exposure starting at 5 days post fertilization

Physiological modifications in near weightlessness, as experienced by astronauts during space flight, have been the subject of numerous studies. Various animal models have been used on space missions or in microgravity simulation on ground to understand the effects of gravity on living animals. Here, we used the zebrafish larvae as a model to study the effect of microgravity simulation on bone formation and whole genome gene expression. To simulate microgravity (sim-μg), we used two-dimensional (2D) clinorotation starting at 5 days post fertilization to assess skeletal formation after 5 days of treatment. To assess early, regulatory effects on gene expression, a single day clinorotation was performed. Clinorotation for 5 days caused a significant decrease of bone formation, as shown by staining for cartilage and bone structures. This effect was not due to stress, as assessed by measuring cortisol levels in treated larvae. Gene expression results indicate that 1-day simulated microgravity affected musculoskeletal, cardiovascular, and nuclear receptor systems. With free-swimming model organisms such as zebrafish larvae, the 2D clinorotation setup appears to be a very appropriate approach to sim-μg. We provide evidence for alterations in bone formation and other important biological functions; in addition several affected genes and pathways involved in bone, muscle or cardiovascular development are identified.

Landmark detection in 2D bioimages for geometric morphometrics: a multi-resolution tree-based approach.

The detection of anatomical landmarks in bioimages is a necessary but tedious step for geometric morphometrics studies in many research domains. We propose variants of a multi-resolution tree-based approach to speed-up the detection of landmarks in bioimages. We extensively evaluate our method variants on three different datasets (cephalometric, zebrafish, and drosophila images). We identify the key method parameters (notably the multi-resolution) and report results with respect to human ground truths and existing methods. Our method achieves recognition performances competitive with current existing approaches while being generic and fast. The algorithms are integrated in the open-source Cytomine software and we provide parameter configuration guidelines so that they can be easily exploited by end-users. Finally, datasets are readily available through a Cytomine server to foster future research.

Areas of Research

This chapter introduces the main topics of research that have benefited so far from the space environment (reduced gravity, ambient radiation, vacuum, etc.), and provides an outlook for future research development. By convention, it is split into two fields: physical sciences/engineering and life sciences.