Automated phenotype pattern recognition of zebrafish for high-throughput screening

Abstract

Over the last years, the zebrafish (Danio rerio) has become a key model organism in genetic and chemical screenings. A growing number of experiments and an expanding interest in zebrafish research makes it increasingly essential to automatize the distribution of embryos and larvae into standard microtiter plates or other sample holders for screening, often according to phenotypical features. Until now, such sorting processes have been carried out by manually handling the larvae and manual feature detection. Here, a prototype platform for image acquisition together with a classification software is presented. Zebrafish embryos and larvae and their features such as pigmentation are detected automatically from the image. Zebrafish of four different phenotypes can be classified through pattern recognition at 72 hours post fertilization (hpf), allowing the software to classify an embryo into two distinct phenotypic classes: wild-type versus variant. The zebrafish phenotypes are classified with an accuracy of 79-99% without any user interaction. A description of the prototype platform and of the algorithms for image processing and pattern recognition is presented.

Streamlining drug discovery assays for cardiovascular disease using zebrafish

“…Although significant developments and improvements regarding the automation of whole-organism screening pipelines ranging from robotics-assisted, microscopic screening platforms to online and real-time parameter acquisition and analysis were made during the recent past [130][131][132][133][134][135][136], it will still take time and efforts to be able to use the zebrafish in fully automated and high-throughput preclinical drug discovery pipelines. Nevertheless, novel approaches including artificial intelligence (AI) and neural network advancements are promising strategies to fill the current gaps thereby enabling streamlined cardiovascular drug discovery [137]. [14] and [51] with permission of Bentham Science Publishers and Elsevier, respectively).…”

High throughput automated detection of axial malformations in Medaka embryo

“…Image processing tools and pattern recognition have been widely used in alevins studies and highthroughput screening [13] [14] [15]. In particular, several articles have shown the efficiency of supervised learning techniques in the scope of alevins phenotypes classification [16].…”

“…Parameters determination for alevin spine segmentation and geometrical description of classification features.By testing different values for the weights − and + (see Equation(15)) associated with the negative positive dataset − (non-malformed alevins) and to the true dataset + (malformed alevins) respectively, we discovered that overall classification accuracy is stable. For 14 different weightings, overall accuracy varies by less than 1%.…”

Automated segmentation of thick confocal microscopy 3D images for the measurement of white matter volumes in zebrafish brains

“…These screens are performed for the study of behaviour [4], gene expressions [10], drug-toxicity [16] or exposure to toxicological compounds [3]. However, image-based screening approaches, which are using whole zebrafish embryos, are mainly performed on the basis of 2D images [17,19]. While 3D-based screening methods do exist, they are either using unconventional microscopy setups, or need multiple acquisitions of the same sample [2,8,14,15,21], which renders them unsuitable for large scale analysis.…”