Unsupervised Learning for Feature Extraction and Temporal Alignment of 3D+t Point Clouds of Zebrafish Embryos

TL;DR

This paper introduces an unsupervised deep learning method that extracts features from 3D+t point clouds of zebrafish embryos and accurately aligns their developmental stages without manual labeling.

Contribution

It proposes an autoencoder-based feature extraction and a deep regression network for temporal alignment, eliminating the need for manual annotations.

Findings

High alignment accuracy with only 3.83 minutes mismatch over 5.3 hours

Fully unsupervised approach reduces manual effort and subjective bias

Scalable method suitable for large datasets

Abstract

Zebrafish are widely used in biomedical research and developmental stages of their embryos often need to be synchronized for further analysis. We present an unsupervised approach to extract descriptive features from 3D+t point clouds of zebrafish embryos and subsequently use those features to temporally align corresponding developmental stages. An autoencoder architecture is proposed to learn a descriptive representation of the point clouds and we designed a deep regression network for their temporal alignment. We achieve a high alignment accuracy with an average mismatch of only 3.83 minutes over an experimental duration of 5.3 hours. As a fully-unsupervised approach, there is no manual labeling effort required and unlike manual analyses the method easily scales. Besides, the alignment without human annotation of the data also avoids any influence caused by subjective bias.