Fully Unsupervised Annotation of C. Elegans

2025-03-10

AI Summary

To address the challenge of constructing spatial atlases for *Caenorhabditis elegans* 3D microscopy images—where ground-truth nuclear annotations are unavailable—we propose the first fully unsupervised nuclear labeling framework. Our method jointly performs cross-sample structural alignment via cycle-consistent multi-image matching and estimates Gaussian distribution parameters for nuclear positions using Bayesian optimization, enabling end-to-end unsupervised modeling. Crucially, it requires no manual annotations. We thereby generate the first unsupervised, whole-lifecycle spatial atlas of all nuclei in *C. elegans*. Quantitatively, our approach achieves localization accuracy comparable to state-of-the-art supervised methods (mean error <1.5 μm), scales efficiently to large image datasets, and is generalizable to other model organisms with invariant cell lineages.

Technology Category

• Machine Learning: Unsupervised & Self-Supervised Learning
• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Medical and Biological Imaging

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

In this work we present a novel approach for unsupervised multi-graph matching, which applies to problems for which a Gaussian distribution of keypoint features can be assumed. We leverage cycle consistency as loss for self-supervised learning, and determine Gaussian parameters through Bayesian Optimization, yielding a highly efficient approach that scales to large datasets. Our fully unsupervised approach enables us to reach the accuracy of state-of-the-art supervised methodology for the use case of annotating cell nuclei in 3D microscopy images of the worm C. elegans. To this end, our approach yields the first unsupervised atlas of C. elegans, i.e. a model of the joint distribution of all of its cell nuclei, without the need for any ground truth cell annotation. This advancement enables highly efficient annotation of cell nuclei in large microscopy datasets of C. elegans. Beyond C. elegans, our approach offers fully unsupervised construction of cell-level atlases for any model organism with a stereotyped cell lineage, and thus bears the potential to catalyze respective comparative developmental studies in a range of further species.

Problem

• Unsupervised multi-graph matching for Gaussian-distributed keypoint features.
• Self-supervised learning using cycle consistency and Bayesian Optimization.
• Creation of unsupervised cell nuclei atlas for C. elegans without ground truth.

Innovation

• Unsupervised multi-graph matching with Gaussian keypoint features
• Cycle consistency loss for self-supervised learning
• Bayesian Optimization for efficient large dataset scaling