The sea urchin embryo represents a well-established model organism widely applied in embryo toxicity assays, ecotoxicological investigations, and biomonitoring studies. These analyses are primarily based on the morphological evaluation of embryos, which is conventionally carried out by experts through light microscopy. However, this approach is both time-intensive and inherently subjective, as the outcomes strongly depend on the evaluator’s expertise and experience. With the increasing adoption of machine learning techniques in image classification tasks, this study investigates the applicability of machine-learning-based approaches for the classification of sea urchin embryo images. The dataset used in this work originates from a previous study examining the effects of nickel exposure on Paracentrotus lividus embryos, with concentrations ranging from 0.01 to 3.0 mM. Given the limited size of the available dataset, data augmentation techniques were applied to artificially expand the number of training samples. Subsequently, a convolutional neural network classification model was developed using both original and augmented images, and its performance was assessed using multiple evaluation metrics. The proposed model demonstrated strong performance, achieving a maximum F1 score of 0.976 and an accuracy of 0.988. These results indicate that machine-learning-based approaches can effectively support the classification of sea urchin embryo images even in data-constrained scenarios. Overall, this work contributes to the development of automated and objective methods for morphological assessment, with the potential to enhance both the reliability and efficiency of traditional evaluation procedures.