A morphology-driven workflow to decipher 3D electron microscopy segmentation in diatoms
Abstract
Cells display diverse shapes, sizes, and internal structures, particularly among microbial species. These differences reflect how cells adapt to their environments and perform essential functions. Modern three-dimensional (3D) electron microscopy captures this diversity at the nanometer scale, but analysis is slow because structures must be outlined manually by experts. Artificial intelligence (AI) has improved image analysis in medical and cell biology research by learning from repeated observations. However, studies of microbial and microalgal biodiversity often rely on single snapshots, complicating automated analysis because AI must learn from static morphology. In this study, we developed an AI-assisted segmentation framework for whole-cell 3D electron microscopy data. By comparing neural network architectures and using transfer learning and contrast-aware strategies, we showed that accurate segmentation is possible with limited training data and standard computing resources. Our method enables faster, reproducible analysis of cellular ultrastructure, supporting large-scale investigations into cell morphology and diversity.
Related
- Automating Nanoparticle Analysis in Transmission Electron Microscopy with Synthetically Trained Segmentation Models
- DeLTA 3.0: A modern segmentation and tracking tool for microscopy images
- SpaCut: Transcript-Aware Morphology Fusion for Robust Cell Segmentation in Subcellular Spatial Transcriptomics.
- Fluorescent Biosensors for Cryogenic Correlative Light and Electron Microscopy
- Crossed laser phase plates for transmission electron microscopy
BibTeX
@article{uwizeye2026morphologydriven,
title = {{A morphology-driven workflow to decipher 3D electron microscopy segmentation in diatoms}},
author = {Clarisse Uwizeye and Serena Flori and Joanell Angulo and Pierre-Henri Jouneau and Benoit Gallet and Pascal Albanese and Giovanni Finazzi},
journal = {Cell Reports Methods},
year = {2026},
month = sep,
doi = {10.1016/j.crmeth.2026.101594},
url = {https://hal.science/hal-05772327v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A morphology-driven workflow to decipher 3D electron microscopy segmentation in diatoms
AU - Clarisse Uwizeye
AU - Serena Flori
AU - Joanell Angulo
AU - Pierre-Henri Jouneau
AU - Benoit Gallet
AU - Pascal Albanese
AU - Giovanni Finazzi
PY - 2026
DA - 2026/09/09
JO - Cell Reports Methods
DO - 10.1016/j.crmeth.2026.101594
UR - https://hal.science/hal-05772327v1
AB - Cells display diverse shapes, sizes, and internal structures, particularly among microbial species. These differences reflect how cells adapt to their environments and perform essential functions. Modern three-dimensional (3D) electron microscopy captures this diversity at the nanometer scale, but analysis is slow because structures must be outlined manually by experts. Artificial intelligence (AI) has improved image analysis in medical and cell biology research by learning from repeated observations. However, studies of microbial and microalgal biodiversity often rely on single snapshots, complicating automated analysis because AI must learn from static morphology. In this study, we developed an AI-assisted segmentation framework for whole-cell 3D electron microscopy data. By comparing neural network architectures and using transfer learning and contrast-aware strategies, we showed that accurate segmentation is possible with limited training data and standard computing resources. Our method enables faster, reproducible analysis of cellular ultrastructure, supporting large-scale investigations into cell morphology and diversity.
SN - 2667-2375
SN - 2667-2375
ER -