Identification of tail curvature malformation in zebrafish embryos

Abstract

Biologists and pharmacologists commonly use zebrafish embryos during the testing of drugs. The testing of these substances is a tedious and painstaking process, carried out manually by trained experts who determine whether the embryos have been deformed or killed as a result of administering the chemical. This paper proposes a novel automatic system for the detection and classification of abnormal curvature of the zebrafish larvae tail (up or down) using a number of geometric features. The most important part of this system is the feature extraction technique, which is done depending on the shape of the tail by applying several arithmetic equations. The proposed system also addresses the orientation problem of the embryos, is part of a larger system for the classification of multiple classes of malformations, and demonstrated a high performance compared to published automated techniques.