Figure 1.
Image Preprocessing: From original image to the one used for classification.
The original image is submitted to an ImageJ script (S1 Fig. for the code) which allows to automatically crop the zebrafish embryo into a square as far as possible. The embryo will be surrounded by a rectangle if it is placed near the sides of the original image. We use a connected-component labeling approach combined with different morphological transformations and binarizations, in order to localize the embryo.
Table 1.
Summary of the effects of the substances used to intoxicate the zebrafish embryos.
Figure 2.
Examples of images representing all the analyzed phenotypes.
“Without phenotype” defect, also called “Normal” embryos (A) are without any phenotype. The “Dead” phenotype (B) is shown as totally necrosed, while the “Chorion” phenotype (C) represents embryos that are still located in their chorion. In “Down Curved Tail” (D), the tail is obviously oriented downward compared to the horizontal. “Hemostasis” (E) presents a small amount of blood which can be located everywhere in the embryo (mainly in the head or in the pericardial area). “Necrosed Yolk Sac” (F) corresponds to a darker yolk compared to normal. In the “Edema” phenotype (G), an edema generally surrounds the anteroventral part of the fish. The “Short Tail” phenotype (H) describes a tail shorter than normal. “Up Curved Fish” (I) and “Up Curved Tail” (J) are two slightly different phenotypes. There is a curvature on the back of the embryo for “Up Curved Fish” (like a kind of lordosis), whereas the curvature is located on the tail for the “Up Curved Tail” phenotype.
Table 2.
Number of images by class (+) and (-) for each phenotype, in the learning set (LS) and the test set (TS).
Table 3.
Summary of the classification results in cross-validation on the learning sets and on the independent test sets using the “All binary” or “Two-tier” method.
Figure 3.
Schematic overview of the Two-tier approach for classification, also showing the recognition rates observed on the test set for the three-class model.
Table 4.
Automatic classification of “difficult” images and “a posteriori” expert agreement.
Table 5.
Chemicals used to intoxicate embryos to build the validation set.
Table 6.
Summary of the classification results on validation set after being classified by the Two-tier approach.
Table 7.
Comparison of the deduced LC50, EC50 and TI for caffeine, DCA and theophylline.
Figure 4.
Dose-response curves for caffeine, theophylline and DCA.
Survival and morphological defects of larvae intoxicated from 2dpf to 3dpf. The fraction of surviving larvae is represented by the “Survival” curve on each graph by a LC50 curve. The EC50 (teratogenicity) curve is drawn according to the results given by the “Normal” phenotype, as the fraction of surviving larvae. A, C, E graphs have been obtained on the basis of manual observations, whereas B, D and F graphs are based on automatic analysis.