Automated Detection of Abnormalities in Zebrafish Development

TL;DR

This paper introduces a large annotated dataset and a transformer-based model for automated detection of developmental abnormalities in zebrafish, improving efficiency and accuracy over manual methods.

Contribution

The work provides the first comprehensive dataset with expert annotations and a baseline transformer model for automated zebrafish toxicity and fertility assessment.

Findings

Achieved 98% accuracy in fertility classification.

Achieved 92% accuracy in toxicity assessment.

Demonstrated the effectiveness of spatiotemporal transformer models.

Abstract

Zebrafish embryos are a valuable model for drug discovery due to their optical transparency and genetic similarity to humans. However, current evaluations rely on manual inspection, which is costly and labor-intensive. While machine learning offers automation potential, progress is limited by the lack of comprehensive datasets. To address this, we introduce a large-scale dataset of high-resolution microscopic image sequences capturing zebrafish embryonic development under both control conditions and exposure to compounds (3,4-dichloroaniline). This dataset, with expert annotations at fine-grained temporal levels, supports two benchmarking tasks: (1) fertility classification, assessing zebrafish egg viability (130,368 images), and (2) toxicity assessment, detecting malformations induced by toxic exposure over time (55,296 images). Alongside the dataset, we present the first transformer-based baseline model that integrates spatiotemporal features to predict developmental abnormalities at early stages. Experimental results present the model's effectiveness, achieving 98% accuracy in fertility classification and 92% in toxicity assessment. These findings underscore the potential of automated approaches to enhance zebrafish-based toxicity analysis.