Automated zebrafish-based toxicity test using Bat optimization and AdaBoost classifier

Abstract

Environmental exposure to toxicants is very important as it become part of our daily life. Therefore, it is necessary to investigate the toxic effects of chemical substances before consuming it. The best choice for performing this test is by applying the toxicants to different animals. The zebrafish embryos are the most suitable animal for this test. In this paper, a fully-automated system is proposed to classify zebrafish embryos to alive or coagulant (i.e. dead due to exposing to toxic compound). The embryos' images are used to extract some features using the Segmentation-based Fractal Texture Analysis (SFTA) technique. Moreover, Bat algorithm is used to select the most discriminative features and then AdaBoost classifier is used to match between testing and training features (i.e. to classify alive and coagulant embryos). The experiments have proved that choosing threshold value of SFTA technique and the selected features have a great impact on the classification accuracy. With classification rate around 98.15%, the experimental results have showed that the proposed model is a very promising step toward a fully-automated toxicity test using zebrafish embryos.