ScholarDeck

Animal / preclinicalTranslational vision science & technology · 2026

Deep-ZOMA: A Deep Learning-Based Approach for Automated Morphometric Analysis of Zebrafish Larvae Ocular Structures.

Youyuan Zhuang, Chuang Xu, Wei Dai … Jianzhong Su

Read paper

OphthalmologyAnimal / preclinical

AI tool measured zebrafish eye structures over 20 times faster than humans, with similar accuracy.

Deep-ZOMA: A Deep Learning-Based Approach for Automated Morphometric Analysis of Zebrafish Larvae Ocular Structures.

Youyuan Zhuang … Jianzhong Su

Translational vision science & technology · 2026

Background

Zebrafish (Danio rerio) ocular measurements are widely used in ocular disease research and drug discovery.

Purpose

Zebrafish (Danio rerio) ocular measurements are widely used in ocular disease research and drug discovery.

Methods

A dual-center dataset of 1820 bright-field images (1010 internal; 810 external) was annotated for key ocular regions.

n = 1820 bright-field images

Results

AI checked eye measurements over 20 times quicker than people, just as accurately

Internal set

0.96Dice c

External set

0.95Dice c

More results

Deep-ZOMA achieved mean Dice coefficients of 0.96 on the internal set and 0.95 on the external set for primary ocular regions, with IoU values >0.90.

Automated measurements showed strong correlations and excellent agreement with expert measurements.

More results

In the slc4a7 model, Deep-ZOMA accurately identified microphthalmia and rescue phenotypes consistent with expert annotations.

“

Conclusion

Deep-ZOMA provides a reliable and efficient solution for high-throughput zebrafish ocular morphometry, supporting applications in ocular genetics, drug screening, and phenotypic studies.

Post

Deep-ZOMA: A Deep Learning-Based Approach for Automated Morphometric Analysis of Zebrafish Larvae Ocular Structures.

AI tool measured zebrafish eye structures over 20 times faster than humans, with similar accuracy.

Related papers